Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1200. Min Range: -8.1200
Max Act: 8.0575. Min Act: -0.1700
Data Index: 5558120 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1200. Min Range: -8.1200
Max Act: 8.0575. Min Act: -0.1700
Data Index: 1286102 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1200. Min Range: -8.1200
Max Act: 8.1200. Min Act: -0.1700
Data Index: 6108973 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.9325. Min Act: -0.1700
Data Index: 3137945 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.9638. Min Act: -0.1700
Data Index: 8700055 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.8388. Min Act: -0.1700
Data Index: 6750841 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.8388. Min Act: -0.1700
Data Index: 2433507 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.7763. Min Act: -0.1700
Data Index: 6571478 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.8075. Min Act: -0.1700
Data Index: 3549930 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.8075. Min Act: -0.1700
Data Index: 8805995 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.7450. Min Act: -0.1700
Data Index: 7358528 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.6513. Min Act: -0.1700
Data Index: 5754508 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.6513. Min Act: -0.1700
Data Index: 6056648 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.6200. Min Act: -0.1700
Data Index: 6688306 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.5575. Min Act: -0.1700
Data Index: 4885062 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.5575. Min Act: -0.1700
Data Index: 8527678 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.5575. Min Act: -0.1700
Data Index: 6610735 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.5263. Min Act: -0.1700
Data Index: 4977959 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.4950. Min Act: -0.1700
Data Index: 1712138 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1200. Min Range: -8.1200
Max Act: 7.4950. Min Act: -0.1700
Data Index: 2600800 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19