Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1626 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.8606. Min Act: -0.1700
Data Index: 3791127 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.7356. Min Act: -0.1700
Data Index: 2258890 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.6106. Min Act: -0.1700
Data Index: 2342141 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2981. Min Act: -0.1700
Data Index: 5213452 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.3606. Min Act: -0.1700
Data Index: 7980733 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.3606. Min Act: -0.1700
Data Index: 5186187 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.3606. Min Act: -0.1700
Data Index: 1150024 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2981. Min Act: -0.1700
Data Index: 6829781 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2981. Min Act: -0.1700
Data Index: 5652445 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.3606. Min Act: -0.1700
Data Index: 6641618 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2981. Min Act: -0.1700
Data Index: 7242411 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2356. Min Act: -0.1700
Data Index: 6783237 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2356. Min Act: -0.1700
Data Index: 4587182 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2356. Min Act: -0.1700
Data Index: 8717816 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.1106. Min Act: -0.1700
Data Index: 6627250 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.1731. Min Act: -0.1700
Data Index: 4888340 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2356. Min Act: -0.1700
Data Index: 372277 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.1731. Min Act: -0.1700
Data Index: 55432 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.2356. Min Act: -0.1700
Data Index: 5923295 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8606. Min Range: -8.8606
Max Act: 8.1731. Min Act: -0.1700
Data Index: 1953655 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19