Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.6528. Min Act: -0.1700
Data Index: 1500458 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.2778. Min Act: -0.1700
Data Index: 8199110 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.2466. Min Act: -0.1700
Data Index: 3335022 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.1841. Min Act: -0.1700
Data Index: 1177423 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.1528. Min Act: -0.1700
Data Index: 928624 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.1216. Min Act: -0.1700
Data Index: 1412547 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.1216. Min Act: -0.1700
Data Index: 5367127 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.1216. Min Act: -0.1700
Data Index: 454621 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.0278. Min Act: -0.1700
Data Index: 2874632 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.0278. Min Act: -0.1700
Data Index: 6994632 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6528. Min Range: -6.6528
Max Act: 6.0278. Min Act: -0.1700
Data Index: 1988257 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9966. Min Act: -0.1700
Data Index: 8204382 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9653. Min Act: -0.1700
Data Index: 7239965 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9966. Min Act: -0.1700
Data Index: 8659805 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9966. Min Act: -0.1700
Data Index: 4686712 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9653. Min Act: -0.1700
Data Index: 795139 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9653. Min Act: -0.1700
Data Index: 767040 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9966. Min Act: -0.1700
Data Index: 8008638 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9653. Min Act: -0.1700
Data Index: 8647921 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6528. Min Range: -6.6528
Max Act: 5.9653. Min Act: -0.1700
Data Index: 6845949 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19