Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 882 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.5324. Min Act: -0.1700
Data Index: 8575832 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.4699. Min Act: -0.1700
Data Index: 6328161 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.4699. Min Act: -0.1700
Data Index: 5291317 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.3449. Min Act: -0.1700
Data Index: 2490624 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.2199. Min Act: -0.1700
Data Index: 7150974 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.2824. Min Act: -0.1700
Data Index: 1245525 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.2824. Min Act: -0.1700
Data Index: 1328080 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.2199. Min Act: -0.1700
Data Index: 2082126 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.0949. Min Act: -0.1700
Data Index: 5230872 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.0949. Min Act: -0.1700
Data Index: 6581464 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.0324. Min Act: -0.1700
Data Index: 5559273 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.9699. Min Act: -0.1700
Data Index: 6919127 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5324. Min Range: -12.5324
Max Act: 12.0324. Min Act: -0.1700
Data Index: 7793504 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.9074. Min Act: -0.1700
Data Index: 5164781 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.9074. Min Act: -0.1700
Data Index: 1586787 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.9074. Min Act: -0.1700
Data Index: 4453563 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.8449. Min Act: -0.1700
Data Index: 4168770 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.9074. Min Act: -0.1700
Data Index: 1110662 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.9074. Min Act: -0.1700
Data Index: 4424201 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5324. Min Range: -12.5324
Max Act: 11.9074. Min Act: -0.1700
Data Index: 2825707 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19