Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5686 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.6426. Min Act: -0.1700
Data Index: 7848382 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.5176. Min Act: -0.1700
Data Index: 5843385 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7946204 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.4239. Min Act: -0.1700
Data Index: 2938756 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.4239. Min Act: -0.1700
Data Index: 2808532 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.3301. Min Act: -0.1700
Data Index: 780376 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.3301. Min Act: -0.1700
Data Index: 617247 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2989. Min Act: -0.1700
Data Index: 5931755 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2989. Min Act: -0.1700
Data Index: 1878411 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2676. Min Act: -0.1700
Data Index: 3021329 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2676. Min Act: -0.1700
Data Index: 4219932 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2364. Min Act: -0.1700
Data Index: 3503767 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2364. Min Act: -0.1700
Data Index: 6684545 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2364. Min Act: -0.1700
Data Index: 5733004 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2051. Min Act: -0.1700
Data Index: 3392468 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2051. Min Act: -0.1700
Data Index: 7465046 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.2051. Min Act: -0.1700
Data Index: 336426 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.1739. Min Act: -0.1700
Data Index: 3563820 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.1426. Min Act: -0.1700
Data Index: 5363582 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6426. Min Range: -5.6426
Max Act: 5.1739. Min Act: -0.1700
Data Index: 6179855 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19