Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.9451. Min Act: -0.1700
Data Index: 603037 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.9139. Min Act: -0.1700
Data Index: 6223514 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.9139. Min Act: -0.1700
Data Index: 2968792 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8826. Min Act: -0.1700
Data Index: 7818352 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8826. Min Act: -0.1700
Data Index: 7691709 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 3189746 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 1669373 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 1674917 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 5827979 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 6016092 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 790735 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8201. Min Act: -0.1700
Data Index: 6667597 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8201. Min Act: -0.1700
Data Index: 3251345 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 4632436 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8201. Min Act: -0.1700
Data Index: 3969518 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.8513. Min Act: -0.1700
Data Index: 2655686 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.7888. Min Act: -0.1700
Data Index: 3675317 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.7888. Min Act: -0.1700
Data Index: 5470389 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.7888. Min Act: -0.1700
Data Index: 2779176 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9451. Min Range: -3.9451
Max Act: 3.7888. Min Act: -0.1700
Data Index: 4137543 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19