Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.9347. Min Act: -0.1700
Data Index: 933091 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.7784. Min Act: -0.1700
Data Index: 3511426 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.3722. Min Act: -0.1700
Data Index: 2747390 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.3409. Min Act: -0.1700
Data Index: 1363853 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.3409. Min Act: -0.1700
Data Index: 5181504 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.2784. Min Act: -0.1700
Data Index: 197414 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.3097. Min Act: -0.1700
Data Index: 5421875 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.3097. Min Act: -0.1700
Data Index: 2087328 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.2784. Min Act: -0.1700
Data Index: 8034488 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.2472. Min Act: -0.1700
Data Index: 2473397 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.2472. Min Act: -0.1700
Data Index: 1238575 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.2159. Min Act: -0.1700
Data Index: 519317 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.2159. Min Act: -0.1700
Data Index: 83398 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.1847. Min Act: -0.1700
Data Index: 2426024 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.1534. Min Act: -0.1700
Data Index: 629249 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.1847. Min Act: -0.1700
Data Index: 2897907 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.1534. Min Act: -0.1700
Data Index: 6457816 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.1222. Min Act: -0.1700
Data Index: 6913825 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.1534. Min Act: -0.1700
Data Index: 7313999 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9347. Min Range: -6.9347
Max Act: 6.1534. Min Act: -0.1700
Data Index: 4703516 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19