Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.7549. Min Act: -0.1700
Data Index: 5760551 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.6454. Min Act: -0.1700
Data Index: 2240029 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.5828. Min Act: -0.1700
Data Index: 1459008 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.5358. Min Act: -0.1700
Data Index: 4383181 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.5358. Min Act: -0.1700
Data Index: 3449744 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.5045. Min Act: -0.1700
Data Index: 508549 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4888. Min Act: -0.1700
Data Index: 1612599 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4888. Min Act: -0.1700
Data Index: 5985862 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4732. Min Act: -0.1700
Data Index: 3190798 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4732. Min Act: -0.1700
Data Index: 3096399 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4732. Min Act: -0.1700
Data Index: 1206049 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4732. Min Act: -0.1700
Data Index: 2575534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4575. Min Act: -0.1700
Data Index: 543772 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4418. Min Act: -0.1700
Data Index: 90950 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4418. Min Act: -0.1700
Data Index: 5666496 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4262. Min Act: -0.1700
Data Index: 3466236 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4105. Min Act: -0.1700
Data Index: 2835534 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4105. Min Act: -0.1700
Data Index: 2210742 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4262. Min Act: -0.1700
Data Index: 999742 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7549. Min Range: -3.7549
Max Act: 3.4105. Min Act: -0.1700
Data Index: 1889590 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19