Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.9434. Min Act: -0.1700
Data Index: 4390648 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.6309. Min Act: -0.1700
Data Index: 7626499 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.5684. Min Act: -0.1700
Data Index: 6748234 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.5059. Min Act: -0.1700
Data Index: 5127490 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.3809. Min Act: -0.1700
Data Index: 1197490 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.3809. Min Act: -0.1700
Data Index: 6371344 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.3184. Min Act: -0.1700
Data Index: 7991344 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.3184. Min Act: -0.1700
Data Index: 7359856 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.2559. Min Act: -0.1700
Data Index: 4472162 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.3184. Min Act: -0.1700
Data Index: 4967889 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.2559. Min Act: -0.1700
Data Index: 358761 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.2559. Min Act: -0.1700
Data Index: 562279 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.2559. Min Act: -0.1700
Data Index: 190881 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.1934. Min Act: -0.1700
Data Index: 6961024 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.1934. Min Act: -0.1700
Data Index: 3735320 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.1934. Min Act: -0.1700
Data Index: 8290861 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.1934. Min Act: -0.1700
Data Index: 2518996 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.1934. Min Act: -0.1700
Data Index: 3152245 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.1934. Min Act: -0.1700
Data Index: 3624087 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9434. Min Range: -8.9434
Max Act: 8.1934. Min Act: -0.1700
Data Index: 4618681 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19