Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2710. Min Range: -10.2710
Max Act: 10.2710. Min Act: -0.1700
Data Index: 5903502 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.9585. Min Act: -0.1700
Data Index: 3277207 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.8960. Min Act: -0.1700
Data Index: 712122 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.7710. Min Act: -0.1700
Data Index: 1256643 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.8335. Min Act: -0.1700
Data Index: 3877304 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.6460. Min Act: -0.1700
Data Index: 7570209 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.6460. Min Act: -0.1700
Data Index: 303136 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.6460. Min Act: -0.1700
Data Index: 2433916 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.5210. Min Act: -0.1700
Data Index: 132358 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.4585. Min Act: -0.1700
Data Index: 1240722 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.4585. Min Act: -0.1700
Data Index: 3993002 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3960. Min Act: -0.1700
Data Index: 6865027 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3960. Min Act: -0.1700
Data Index: 974362 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3335. Min Act: -0.1700
Data Index: 4670232 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3335. Min Act: -0.1700
Data Index: 3590169 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3960. Min Act: -0.1700
Data Index: 5839168 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3960. Min Act: -0.1700
Data Index: 2252728 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3335. Min Act: -0.1700
Data Index: 4200423 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3335. Min Act: -0.1700
Data Index: 3962098 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2710. Min Range: -10.2710
Max Act: 9.3335. Min Act: -0.1700
Data Index: 4480761 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19