Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.7310. Min Act: -0.1700
Data Index: 7885994 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6998. Min Act: -0.1698
Data Index: 7775418 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6685. Min Act: -0.1700
Data Index: 4640661 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6685. Min Act: -0.1700
Data Index: 6315248 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6373. Min Act: -0.1700
Data Index: 3051669 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6373. Min Act: -0.1700
Data Index: 1733676 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6373. Min Act: -0.1700
Data Index: 2703328 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6060. Min Act: -0.1700
Data Index: 1488011 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6060. Min Act: -0.1700
Data Index: 1985175 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6060. Min Act: -0.1700
Data Index: 3501681 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6060. Min Act: -0.1700
Data Index: 940697 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.6060. Min Act: -0.1700
Data Index: 2421858 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5435. Min Act: -0.1700
Data Index: 3335340 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5748. Min Act: -0.1700
Data Index: 2695321 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5748. Min Act: -0.1700
Data Index: 2160001 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5435. Min Act: -0.1700
Data Index: 4783931 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5435. Min Act: -0.1700
Data Index: 8503732 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5123. Min Act: -0.1700
Data Index: 3425917 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5123. Min Act: -0.1700
Data Index: 8289741 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7310. Min Range: -6.7310
Max Act: 6.5123. Min Act: -0.1700
Data Index: 1077224 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19