Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.5443. Min Act: -0.1700
Data Index: 4440321 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.3876. Min Act: -0.1700
Data Index: 4989973 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.3249. Min Act: -0.1700
Data Index: 716113 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.3249. Min Act: -0.1700
Data Index: 3128713 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.3249. Min Act: -0.1700
Data Index: 854402 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2778. Min Act: -0.1700
Data Index: 3711150 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2935. Min Act: -0.1700
Data Index: 7421940 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2935. Min Act: -0.1700
Data Index: 2840393 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2621. Min Act: -0.1700
Data Index: 7308100 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2464. Min Act: -0.1700
Data Index: 7847258 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2464. Min Act: -0.1700
Data Index: 5120404 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2307. Min Act: -0.1700
Data Index: 6625045 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2149. Min Act: -0.1700
Data Index: 2031849 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.2149. Min Act: -0.1700
Data Index: 8382590 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.1835. Min Act: -0.1700
Data Index: 4004437 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.1992. Min Act: -0.1700
Data Index: 5120403 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.1992. Min Act: -0.1700
Data Index: 3047175 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.1835. Min Act: -0.1700
Data Index: 1071203 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.1835. Min Act: -0.1700
Data Index: 3666965 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5443. Min Range: -3.5443
Max Act: 3.1678. Min Act: -0.1700
Data Index: 2607699 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19