Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0128. Min Range: -5.0128
Max Act: 5.0128. Min Act: -0.1700
Data Index: 1128883 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0128. Min Range: -5.0128
Max Act: 5.0128. Min Act: -0.1700
Data Index: 6129591 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0128. Min Range: -5.0128
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4388708 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9816. Min Act: -0.1700
Data Index: 3513203 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9816. Min Act: -0.1700
Data Index: 317417 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9816. Min Act: -0.1700
Data Index: 3448786 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9191. Min Act: -0.1700
Data Index: 6492939 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9191. Min Act: -0.1700
Data Index: 2724641 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9191. Min Act: -0.1700
Data Index: 1800005 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.9191. Min Act: -0.1700
Data Index: 7155099 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 6492937 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 7688817 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 8253201 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 5513499 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 7179231 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 4269361 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 3917684 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 3351326 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 5824591 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0128. Min Range: -5.0128
Max Act: 4.8566. Min Act: -0.1700
Data Index: 323880 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19