Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0821. Min Range: -4.0821
Max Act: 4.0821. Min Act: -0.1700
Data Index: 1280496 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.9571. Min Act: -0.1700
Data Index: 7871877 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.9571. Min Act: -0.1700
Data Index: 5559703 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.9571. Min Act: -0.1700
Data Index: 278360 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.9258. Min Act: -0.1700
Data Index: 613059 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.8946. Min Act: -0.1700
Data Index: 3792113 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.8633. Min Act: -0.1700
Data Index: 3635705 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.8946. Min Act: -0.1700
Data Index: 796588 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.8320. Min Act: -0.1700
Data Index: 1201765 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.8320. Min Act: -0.1700
Data Index: 2902235 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.8008. Min Act: -0.1700
Data Index: 3649298 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.8008. Min Act: -0.1700
Data Index: 191314 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7695. Min Act: -0.1700
Data Index: 1404065 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7539. Min Act: -0.1700
Data Index: 7359637 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7539. Min Act: -0.1700
Data Index: 8405414 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7539. Min Act: -0.1700
Data Index: 8389003 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7539. Min Act: -0.1700
Data Index: 8340491 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7539. Min Act: -0.1700
Data Index: 4798148 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7382. Min Act: -0.1700
Data Index: 2634704 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0821. Min Range: -4.0821
Max Act: 3.7226. Min Act: -0.1700
Data Index: 6176154 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19