Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1197. Min Range: -6.1197
Max Act: 6.1197. Min Act: -0.1700
Data Index: 673793 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.7135. Min Act: -0.1700
Data Index: 3044856 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.6197. Min Act: -0.1700
Data Index: 3420496 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.5885. Min Act: -0.1700
Data Index: 8790325 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.5260. Min Act: -0.1700
Data Index: 5513764 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.5260. Min Act: -0.1700
Data Index: 456599 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 3551173 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.5260. Min Act: -0.1700
Data Index: 606023 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.5260. Min Act: -0.1700
Data Index: 6905642 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 7906828 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.4635. Min Act: -0.1700
Data Index: 2342438 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.4635. Min Act: -0.1700
Data Index: 7792144 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.4010. Min Act: -0.1700
Data Index: 4899768 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.4010. Min Act: -0.1700
Data Index: 1226645 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.4010. Min Act: -0.1700
Data Index: 488170 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 5461349 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.3385. Min Act: -0.1700
Data Index: 1493196 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.3385. Min Act: -0.1700
Data Index: 7565475 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 8536430 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1197. Min Range: -6.1197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 4469690 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19