Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.7815. Min Act: -0.1700
Data Index: 1991351 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.7502. Min Act: -0.1700
Data Index: 174960 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.6565. Min Act: -0.1700
Data Index: 4067994 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.6565. Min Act: -0.1700
Data Index: 8663788 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.6565. Min Act: -0.1700
Data Index: 1623669 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.6565. Min Act: -0.1700
Data Index: 174961 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5940. Min Act: -0.1700
Data Index: 8383438 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5940. Min Act: -0.1700
Data Index: 8401906 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5940. Min Act: -0.1700
Data Index: 1196744 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.6252. Min Act: -0.1700
Data Index: 2128402 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5627. Min Act: -0.1700
Data Index: 2449597 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5627. Min Act: -0.1700
Data Index: 8160276 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5627. Min Act: -0.1700
Data Index: 2068285 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5627. Min Act: -0.1700
Data Index: 1827307 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5315. Min Act: -0.1700
Data Index: 1012971 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5315. Min Act: -0.1700
Data Index: 8236443 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5315. Min Act: -0.1700
Data Index: 3715842 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5315. Min Act: -0.1700
Data Index: 2576833 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.4690. Min Act: -0.1700
Data Index: 6285353 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7815. Min Range: -5.7815
Max Act: 5.5315. Min Act: -0.1700
Data Index: 998405 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19