Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3944 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.9245. Min Act: -0.1700
Data Index: 922486 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.7974. Min Act: -0.1700
Data Index: 2143464 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.7656. Min Act: -0.1700
Data Index: 6657535 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.7336. Min Act: -0.1700
Data Index: 6835418 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.7017. Min Act: -0.1700
Data Index: 3149433 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.7017. Min Act: -0.1700
Data Index: 6039108 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.6696. Min Act: -0.1700
Data Index: 315602 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.6536. Min Act: -0.1700
Data Index: 8072312 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.6054. Min Act: -0.1700
Data Index: 158073 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.6054. Min Act: -0.1700
Data Index: 6304613 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5893. Min Act: -0.1700
Data Index: 754386 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5893. Min Act: -0.1700
Data Index: 1821014 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5893. Min Act: -0.1700
Data Index: 7867455 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5732. Min Act: -0.1700
Data Index: 664602 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5732. Min Act: -0.1700
Data Index: 6576707 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5409. Min Act: -0.1700
Data Index: 5598280 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5570. Min Act: -0.1700
Data Index: 2947154 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5570. Min Act: -0.1700
Data Index: 4524118 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5409. Min Act: -0.1700
Data Index: 6495598 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9245. Min Range: -2.9245
Max Act: 2.5570. Min Act: -0.1700
Data Index: 754387 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19