Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1273. Min Range: -6.1273
Max Act: 6.1273. Min Act: -0.1700
Data Index: 2274951 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1273. Min Range: -6.1273
Max Act: 6.0961. Min Act: -0.1700
Data Index: 6796880 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1273. Min Range: -6.1273
Max Act: 6.0648. Min Act: -0.1700
Data Index: 2639141 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1273. Min Range: -6.1273
Max Act: 6.0023. Min Act: -0.1700
Data Index: 8751347 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.9086. Min Act: -0.1700
Data Index: 1674756 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.9086. Min Act: -0.1700
Data Index: 7779911 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.8461. Min Act: -0.1700
Data Index: 1265627 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.8461. Min Act: -0.1700
Data Index: 2352566 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.8461. Min Act: -0.1700
Data Index: 804866 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.8461. Min Act: -0.1700
Data Index: 7457731 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.8148. Min Act: -0.1700
Data Index: 486221 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.7836. Min Act: -0.1700
Data Index: 286301 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.8148. Min Act: -0.1700
Data Index: 6003858 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.8148. Min Act: -0.1700
Data Index: 288216 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.7836. Min Act: -0.1700
Data Index: 5474951 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.7836. Min Act: -0.1700
Data Index: 4112393 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.7523. Min Act: -0.1700
Data Index: 3325914 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.7211. Min Act: -0.1700
Data Index: 7326084 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.7211. Min Act: -0.1700
Data Index: 49883 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.7211. Min Act: -0.1700
Data Index: 7524477 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19