Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.3447. Min Act: -0.1700
Data Index: 3657426 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.2509. Min Act: -0.1700
Data Index: 2734056 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.1884. Min Act: -0.1700
Data Index: 3467756 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.1884. Min Act: -0.1700
Data Index: 2603546 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.1884. Min Act: -0.1700
Data Index: 3450042 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.1259. Min Act: -0.1700
Data Index: 7063597 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.0947. Min Act: -0.1700
Data Index: 2437891 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.0634. Min Act: -0.1700
Data Index: 2728800 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.0009. Min Act: -0.1700
Data Index: 2329144 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.0009. Min Act: -0.1700
Data Index: 7621445 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.0009. Min Act: -0.1700
Data Index: 8297493 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3447. Min Range: -6.3447
Max Act: 6.0009. Min Act: -0.1700
Data Index: 4750737 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.9384. Min Act: -0.1700
Data Index: 1620535 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.9697. Min Act: -0.1700
Data Index: 7048478 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.9384. Min Act: -0.1700
Data Index: 6503432 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.8759. Min Act: -0.1700
Data Index: 5239817 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.8759. Min Act: -0.1700
Data Index: 6120990 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.8759. Min Act: -0.1700
Data Index: 132966 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.8759. Min Act: -0.1700
Data Index: 1195484 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3447. Min Range: -6.3447
Max Act: 5.8759. Min Act: -0.1700
Data Index: 556769 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19