Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.5812. Min Act: -0.1700
Data Index: 236493 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.4874. Min Act: -0.1700
Data Index: 1978824 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.4874. Min Act: -0.1700
Data Index: 1428544 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.4874. Min Act: -0.1700
Data Index: 123139 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.4249. Min Act: -0.1700
Data Index: 6087763 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.4249. Min Act: -0.1700
Data Index: 7219412 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3937. Min Act: -0.1700
Data Index: 3660625 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3937. Min Act: -0.1700
Data Index: 2417515 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3937. Min Act: -0.1700
Data Index: 6057360 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3937. Min Act: -0.1700
Data Index: 5406227 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3312. Min Act: -0.1700
Data Index: 5659587 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3312. Min Act: -0.1700
Data Index: 8637831 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3312. Min Act: -0.1700
Data Index: 3920695 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.3312. Min Act: -0.1700
Data Index: 6702958 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.2999. Min Act: -0.1700
Data Index: 8824599 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.2687. Min Act: -0.1700
Data Index: 6454336 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.2374. Min Act: -0.1700
Data Index: 7038841 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.2374. Min Act: -0.1700
Data Index: 2745610 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.2374. Min Act: -0.1700
Data Index: 5381567 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5812. Min Range: -4.5812
Max Act: 4.2374. Min Act: -0.1700
Data Index: 2020058 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19