Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3739 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.8323. Min Act: -0.1700
Data Index: 3899398 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.7698. Min Act: -0.1700
Data Index: 2365630 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.5823. Min Act: -0.1700
Data Index: 7729826 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.5823. Min Act: -0.1700
Data Index: 1157156 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.5198. Min Act: -0.1700
Data Index: 3043583 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.5198. Min Act: -0.1700
Data Index: 5560026 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.4573. Min Act: -0.1700
Data Index: 8266491 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.5198. Min Act: -0.1700
Data Index: 5609096 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.4573. Min Act: -0.1700
Data Index: 5844139 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.3948. Min Act: -0.1700
Data Index: 7322195 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.3323. Min Act: -0.1700
Data Index: 4960319 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.3323. Min Act: -0.1700
Data Index: 5942203 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.3323. Min Act: -0.1700
Data Index: 653879 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.3323. Min Act: -0.1700
Data Index: 2911618 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.3323. Min Act: -0.1700
Data Index: 6139643 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.2698. Min Act: -0.1700
Data Index: 5386896 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.2698. Min Act: -0.1700
Data Index: 6125343 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.2698. Min Act: -0.1700
Data Index: 8266473 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.2698. Min Act: -0.1700
Data Index: 1142414 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8323. Min Range: -10.8323
Max Act: 10.2698. Min Act: -0.1700
Data Index: 5519732 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19