Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.5196. Min Act: -0.1700
Data Index: 4048350 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.3315. Min Act: -0.1700
Data Index: 2458218 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.3315. Min Act: -0.1700
Data Index: 7707654 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2844. Min Act: -0.1700
Data Index: 3545071 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.3001. Min Act: -0.1700
Data Index: 5120638 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.3001. Min Act: -0.1700
Data Index: 3623156 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.3001. Min Act: -0.1700
Data Index: 8325443 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.3001. Min Act: -0.1700
Data Index: 5882844 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2844. Min Act: -0.1700
Data Index: 6844833 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2530. Min Act: -0.1700
Data Index: 5289184 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2530. Min Act: -0.1700
Data Index: 5243529 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2216. Min Act: -0.1700
Data Index: 748371 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2059. Min Act: -0.1700
Data Index: 5950308 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2059. Min Act: -0.1700
Data Index: 7209390 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2059. Min Act: -0.1700
Data Index: 562013 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.2059. Min Act: -0.1700
Data Index: 8596081 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.1902. Min Act: -0.1700
Data Index: 5117011 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.1744. Min Act: -0.1700
Data Index: 7464920 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.1744. Min Act: -0.1700
Data Index: 553096 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5196. Min Range: -3.5196
Max Act: 3.1744. Min Act: -0.1700
Data Index: 935868 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19