Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 1648179 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1044. Min Act: -0.1700
Data Index: 5922815 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1044. Min Act: -0.1700
Data Index: 2370070 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1044. Min Act: -0.1700
Data Index: 6418569 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 380398 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 259328 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0419. Min Act: -0.1700
Data Index: 3640298 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 7186081 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 7790804 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.9794. Min Act: -0.1700
Data Index: 7306995 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.9481. Min Act: -0.1700
Data Index: 598877 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.9481. Min Act: -0.1700
Data Index: 8411188 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.8544. Min Act: -0.1700
Data Index: 5658030 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.8544. Min Act: -0.1700
Data Index: 2690760 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.8231. Min Act: -0.1700
Data Index: 8283628 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.8231. Min Act: -0.1700
Data Index: 4984585 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.8231. Min Act: -0.1700
Data Index: 6253657 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.8231. Min Act: -0.1700
Data Index: 6424602 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.8231. Min Act: -0.1700
Data Index: 3832310 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.7919. Min Act: -0.1700
Data Index: 3918022 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19