Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.5362. Min Act: -0.1700
Data Index: 7214705 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.4892. Min Act: -0.1700
Data Index: 5613858 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.4265. Min Act: -0.1700
Data Index: 4146133 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.4265. Min Act: -0.1700
Data Index: 3765626 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3795. Min Act: -0.1700
Data Index: 7906881 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3638. Min Act: -0.1700
Data Index: 5516352 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3638. Min Act: -0.1700
Data Index: 7214703 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3481. Min Act: -0.1700
Data Index: 5731170 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3324. Min Act: -0.1700
Data Index: 3206482 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3324. Min Act: -0.1700
Data Index: 7360427 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3324. Min Act: -0.1700
Data Index: 3293029 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3481. Min Act: -0.1700
Data Index: 1781956 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.3167. Min Act: -0.1700
Data Index: 7143947 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.2696. Min Act: -0.1700
Data Index: 7069493 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.2539. Min Act: -0.1700
Data Index: 4780385 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.2382. Min Act: -0.1700
Data Index: 3981676 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.2382. Min Act: -0.1700
Data Index: 7426805 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.2382. Min Act: -0.1700
Data Index: 3368095 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.2382. Min Act: -0.1700
Data Index: 1075335 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5362. Min Range: -3.5362
Max Act: 3.2068. Min Act: -0.1700
Data Index: 1348186 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19