Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.6327. Min Act: -0.1700
Data Index: 6739792 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.5702. Min Act: -0.1700
Data Index: 3870110 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.5390. Min Act: -0.1700
Data Index: 4521536 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.5077. Min Act: -0.1700
Data Index: 4582374 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.4452. Min Act: -0.1700
Data Index: 1564063 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.4140. Min Act: -0.1700
Data Index: 5879297 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.4140. Min Act: -0.1700
Data Index: 2184279 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.4140. Min Act: -0.1700
Data Index: 355897 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3827. Min Act: -0.1700
Data Index: 647271 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3827. Min Act: -0.1700
Data Index: 5044612 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3515. Min Act: -0.1700
Data Index: 6827979 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3515. Min Act: -0.1700
Data Index: 259320 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3515. Min Act: -0.1700
Data Index: 3049361 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3202. Min Act: -0.1700
Data Index: 7379962 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3202. Min Act: -0.1700
Data Index: 666711 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3515. Min Act: -0.1700
Data Index: 96271 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.3202. Min Act: -0.1700
Data Index: 4784356 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.2890. Min Act: -0.1700
Data Index: 1893744 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.2577. Min Act: -0.1700
Data Index: 1100140 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6327. Min Range: -4.6327
Max Act: 4.2577. Min Act: -0.1700
Data Index: 3772997 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19