Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5215 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2223. Min Range: -7.2223
Max Act: 7.2223. Min Act: -0.1700
Data Index: 5825974 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2223. Min Range: -7.2223
Max Act: 7.1285. Min Act: -0.1700
Data Index: 2076277 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2223. Min Range: -7.2223
Max Act: 7.0973. Min Act: -0.1700
Data Index: 5265567 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2223. Min Range: -7.2223
Max Act: 7.0035. Min Act: -0.1700
Data Index: 1850286 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.9098. Min Act: -0.1700
Data Index: 1281197 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.8473. Min Act: -0.1700
Data Index: 2636031 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.8160. Min Act: -0.1700
Data Index: 4679246 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.7535. Min Act: -0.1700
Data Index: 465213 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.7535. Min Act: -0.1700
Data Index: 3137613 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.7223. Min Act: -0.1700
Data Index: 1414357 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.6910. Min Act: -0.1700
Data Index: 3201577 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.6910. Min Act: -0.1700
Data Index: 5290105 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.7223. Min Act: -0.1700
Data Index: 5351682 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.6598. Min Act: -0.1700
Data Index: 7516079 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.6598. Min Act: -0.1700
Data Index: 1005169 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.6285. Min Act: -0.1700
Data Index: 735351 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.6285. Min Act: -0.1700
Data Index: 5107814 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.5973. Min Act: -0.1700
Data Index: 977676 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.5973. Min Act: -0.1700
Data Index: 376730 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2223. Min Range: -7.2223
Max Act: 6.5973. Min Act: -0.1700
Data Index: 4193478 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19