Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1893 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.6975. Min Act: -0.1700
Data Index: 2011689 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.5412. Min Act: -0.1700
Data Index: 6127173 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.4787. Min Act: -0.1700
Data Index: 2774284 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.4787. Min Act: -0.1700
Data Index: 1933417 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.4787. Min Act: -0.1700
Data Index: 5418021 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.4475. Min Act: -0.1700
Data Index: 2620265 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3850. Min Act: -0.1700
Data Index: 4155301 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3850. Min Act: -0.1700
Data Index: 3575434 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.4162. Min Act: -0.1700
Data Index: 1011510 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3850. Min Act: -0.1700
Data Index: 8479466 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3537. Min Act: -0.1700
Data Index: 1177255 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3537. Min Act: -0.1700
Data Index: 2034085 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3537. Min Act: -0.1700
Data Index: 4720179 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3225. Min Act: -0.1700
Data Index: 5686041 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3225. Min Act: -0.1700
Data Index: 2994295 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3225. Min Act: -0.1700
Data Index: 6965342 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.2912. Min Act: -0.1700
Data Index: 6345073 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.2912. Min Act: -0.1700
Data Index: 1757086 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.2912. Min Act: -0.1700
Data Index: 6275255 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6975. Min Range: -4.6975
Max Act: 4.3225. Min Act: -0.1700
Data Index: 1011508 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19