Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5603. Min Range: -7.5603
Max Act: 7.5603. Min Act: -0.1700
Data Index: 356065 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5603. Min Range: -7.5603
Max Act: 7.1228. Min Act: -0.1700
Data Index: 3525925 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5603. Min Range: -7.5603
Max Act: 7.0603. Min Act: -0.1700
Data Index: 3765585 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5603. Min Range: -7.5603
Max Act: 7.0291. Min Act: -0.1700
Data Index: 3473662 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.9353. Min Act: -0.1700
Data Index: 8477013 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.9353. Min Act: -0.1700
Data Index: 3242655 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.9353. Min Act: -0.1700
Data Index: 4953738 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5830586 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.9041. Min Act: -0.1700
Data Index: 1714685 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.7478. Min Act: -0.1700
Data Index: 4392109 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.7478. Min Act: -0.1700
Data Index: 794046 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.7478. Min Act: -0.1700
Data Index: 6235190 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.6853. Min Act: -0.1700
Data Index: 6573710 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.6541. Min Act: -0.1700
Data Index: 4535903 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.6228. Min Act: -0.1700
Data Index: 3270840 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.6228. Min Act: -0.1700
Data Index: 2616528 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.6541. Min Act: -0.1700
Data Index: 7832485 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.5916. Min Act: -0.1700
Data Index: 5835503 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.5603. Min Act: -0.1700
Data Index: 4501812 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5603. Min Range: -7.5603
Max Act: 6.5603. Min Act: -0.1700
Data Index: 6563921 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19