Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5905. Min Act: -0.1700
Data Index: 4636379 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5905. Min Act: -0.1700
Data Index: 5526214 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5592. Min Act: -0.1700
Data Index: 3263726 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5279. Min Act: -0.1700
Data Index: 6041693 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5279. Min Act: -0.1700
Data Index: 6621446 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4809. Min Act: -0.1700
Data Index: 4160202 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4966. Min Act: -0.1700
Data Index: 384733 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4496. Min Act: -0.1700
Data Index: 5420530 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4653. Min Act: -0.1700
Data Index: 6636427 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4496. Min Act: -0.1700
Data Index: 6163469 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4182. Min Act: -0.1700
Data Index: 4160203 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4182. Min Act: -0.1700
Data Index: 2093886 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3869. Min Act: -0.1700
Data Index: 384732 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3398. Min Act: -0.1700
Data Index: 7950181 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3241. Min Act: -0.1700
Data Index: 282536 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3084. Min Act: -0.1700
Data Index: 2929832 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3084. Min Act: -0.1700
Data Index: 2616371 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3084. Min Act: -0.1700
Data Index: 420962 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.2927. Min Act: -0.1700
Data Index: 3113352 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.2927. Min Act: -0.1700
Data Index: 746891 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19