Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2978. Min Range: -7.2978
Max Act: 7.2978. Min Act: -0.1700
Data Index: 996530 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2978. Min Range: -7.2978
Max Act: 7.0166. Min Act: -0.1700
Data Index: 3219455 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2978. Min Range: -7.2978
Max Act: 7.0166. Min Act: -0.1700
Data Index: 3219457 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.9541. Min Act: -0.1700
Data Index: 3219456 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.8291. Min Act: -0.1700
Data Index: 4900564 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.8291. Min Act: -0.1700
Data Index: 1657402 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.7978. Min Act: -0.1700
Data Index: 1922388 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.7978. Min Act: -0.1700
Data Index: 5348050 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.7353. Min Act: -0.1700
Data Index: 7545395 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.7041. Min Act: -0.1700
Data Index: 977423 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.7353. Min Act: -0.1700
Data Index: 970509 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.7041. Min Act: -0.1700
Data Index: 3229854 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.7041. Min Act: -0.1700
Data Index: 6335564 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.6728. Min Act: -0.1700
Data Index: 4957283 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.6416. Min Act: -0.1700
Data Index: 7151770 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.6728. Min Act: -0.1700
Data Index: 6077431 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.6103. Min Act: -0.1700
Data Index: 5563144 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.6103. Min Act: -0.1700
Data Index: 1876016 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.6103. Min Act: -0.1700
Data Index: 265499 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2978. Min Range: -7.2978
Max Act: 6.6103. Min Act: -0.1700
Data Index: 5867462 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19