Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4928. Min Range: -12.4928
Max Act: 12.4928. Min Act: -0.1700
Data Index: 8418502 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4928. Min Range: -12.4928
Max Act: 12.3053. Min Act: -0.1700
Data Index: 6480700 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.8053. Min Act: -0.1700
Data Index: 6577086 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.6803. Min Act: -0.1700
Data Index: 2541718 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.6178. Min Act: -0.1700
Data Index: 5261819 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.6178. Min Act: -0.1700
Data Index: 6535911 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.5553. Min Act: -0.1700
Data Index: 4942658 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.5553. Min Act: -0.1700
Data Index: 3366846 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.4303. Min Act: -0.1700
Data Index: 3385459 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.3678. Min Act: -0.1700
Data Index: 1571386 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.3678. Min Act: -0.1700
Data Index: 7970668 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.3678. Min Act: -0.1700
Data Index: 5236637 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.1803. Min Act: -0.1700
Data Index: 3772166 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.1803. Min Act: -0.1700
Data Index: 3216386 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.1803. Min Act: -0.1700
Data Index: 5814452 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.1178. Min Act: -0.1700
Data Index: 2393278 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.1178. Min Act: -0.1700
Data Index: 8492037 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.1178. Min Act: -0.1700
Data Index: 3550977 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.0553. Min Act: -0.1700
Data Index: 5461598 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4928. Min Range: -12.4928
Max Act: 11.0553. Min Act: -0.1700
Data Index: 2899098 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19