Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5665 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0378. Min Range: -6.0378
Max Act: 6.0378. Min Act: -0.1700
Data Index: 5993934 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0378. Min Range: -6.0378
Max Act: 6.0066. Min Act: -0.1698
Data Index: 561838 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9753. Min Act: -0.1700
Data Index: 906943 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9753. Min Act: -0.1700
Data Index: 379014 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9753. Min Act: -0.1700
Data Index: 766221 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9441. Min Act: -0.1699
Data Index: 5731225 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.9128. Min Act: -0.1700
Data Index: 5708128 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8816. Min Act: -0.1700
Data Index: 5170088 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8503. Min Act: -0.1693
Data Index: 5584970 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8816. Min Act: -0.1700
Data Index: 4415863 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8503. Min Act: -0.1700
Data Index: 5989675 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8503. Min Act: -0.1700
Data Index: 6119450 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8503. Min Act: -0.1700
Data Index: 2857192 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8191. Min Act: -0.1696
Data Index: 7406719 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8191. Min Act: -0.1700
Data Index: 3835977 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8191. Min Act: -0.1698
Data Index: 7398808 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8503. Min Act: -0.1700
Data Index: 7034058 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8191. Min Act: -0.1700
Data Index: 3224478 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.8191. Min Act: -0.1700
Data Index: 928282 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0378. Min Range: -6.0378
Max Act: 5.7566. Min Act: -0.1700
Data Index: 4211495 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19