Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.9586. Min Act: -0.1700
Data Index: 427687 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.5836. Min Act: -0.1700
Data Index: 862700 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.5523. Min Act: -0.1700
Data Index: 8246408 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.5211. Min Act: -0.1700
Data Index: 8594133 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.5211. Min Act: -0.1700
Data Index: 2670147 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.5211. Min Act: -0.1700
Data Index: 7317115 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4898. Min Act: -0.1700
Data Index: 6737479 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4898. Min Act: -0.1700
Data Index: 5636334 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4898. Min Act: -0.1700
Data Index: 5933009 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4898. Min Act: -0.1700
Data Index: 1696123 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4586. Min Act: -0.1700
Data Index: 8309102 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4586. Min Act: -0.1700
Data Index: 6668842 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4898. Min Act: -0.1700
Data Index: 5411168 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4586. Min Act: -0.1700
Data Index: 8260345 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4273. Min Act: -0.1700
Data Index: 4096355 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4586. Min Act: -0.1700
Data Index: 827726 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4586. Min Act: -0.1700
Data Index: 1860569 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.3961. Min Act: -0.1700
Data Index: 6792665 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4273. Min Act: -0.1700
Data Index: 5862674 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9586. Min Range: -4.9586
Max Act: 4.4273. Min Act: -0.1700
Data Index: 5897336 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19