Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5297 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.9832. Min Act: -0.1700
Data Index: 4522610 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.8582. Min Act: -0.1700
Data Index: 4632240 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.8582. Min Act: -0.1700
Data Index: 2848485 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.7332. Min Act: -0.1700
Data Index: 8398411 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.6707. Min Act: -0.1700
Data Index: 1845097 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.6395. Min Act: -0.1700
Data Index: 7442020 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.6395. Min Act: -0.1700
Data Index: 3585699 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.5457. Min Act: -0.1700
Data Index: 4327091 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.5770. Min Act: -0.1700
Data Index: 1494135 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.5457. Min Act: -0.1700
Data Index: 2275340 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.5145. Min Act: -0.1700
Data Index: 3181258 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.5457. Min Act: -0.1700
Data Index: 2292221 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.5145. Min Act: -0.1700
Data Index: 97928 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.4832. Min Act: -0.1700
Data Index: 7947501 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.4832. Min Act: -0.1700
Data Index: 2355096 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.4520. Min Act: -0.1700
Data Index: 3376142 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.4207. Min Act: -0.1700
Data Index: 1413716 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.4520. Min Act: -0.1700
Data Index: 6183188 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.4207. Min Act: -0.1700
Data Index: 1429855 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9832. Min Range: -7.9832
Max Act: 7.4207. Min Act: -0.1700
Data Index: 1940342 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19