Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.9359. Min Act: -0.1700
Data Index: 2632316 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.7484. Min Act: -0.1700
Data Index: 5535337 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.7172. Min Act: -0.1700
Data Index: 165717 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.6547. Min Act: -0.1700
Data Index: 4416759 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.6234. Min Act: -0.1700
Data Index: 7273504 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.6547. Min Act: -0.1700
Data Index: 7856767 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5922. Min Act: -0.1700
Data Index: 5639613 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.6234. Min Act: -0.1700
Data Index: 7141380 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.6234. Min Act: -0.1700
Data Index: 3589875 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.6234. Min Act: -0.1700
Data Index: 4327930 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5922. Min Act: -0.1700
Data Index: 3859740 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5922. Min Act: -0.1700
Data Index: 3771323 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5922. Min Act: -0.1700
Data Index: 11653 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5609. Min Act: -0.1700
Data Index: 5268116 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5609. Min Act: -0.1700
Data Index: 7543182 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5609. Min Act: -0.1700
Data Index: 6711280 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5609. Min Act: -0.1700
Data Index: 1349904 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5609. Min Act: -0.1700
Data Index: 6153570 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5297. Min Act: -0.1700
Data Index: 3478741 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9359. Min Range: -5.9359
Max Act: 5.5297. Min Act: -0.1700
Data Index: 1042976 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19