Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4096 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8948. Min Act: -0.1700
Data Index: 7301454 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 7789015 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8011. Min Act: -0.1700
Data Index: 3951768 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8011. Min Act: -0.1700
Data Index: 6474039 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 387929 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 7123890 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 8311954 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 6513966 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 8090103 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7386. Min Act: -0.1700
Data Index: 3831884 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7073. Min Act: -0.1700
Data Index: 8203473 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7073. Min Act: -0.1700
Data Index: 3189021 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7073. Min Act: -0.1700
Data Index: 2025627 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.6761. Min Act: -0.1700
Data Index: 3411218 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7073. Min Act: -0.1700
Data Index: 3768259 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.6448. Min Act: -0.1700
Data Index: 2561581 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.6136. Min Act: -0.1700
Data Index: 1389660 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.6136. Min Act: -0.1700
Data Index: 6855540 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.6136. Min Act: -0.1700
Data Index: 7301455 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.5823. Min Act: -0.1700
Data Index: 3573508 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19