Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.7473. Min Act: -0.1700
Data Index: 3346153 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.5286. Min Act: -0.1700
Data Index: 246663 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.5598. Min Act: -0.1700
Data Index: 3841351 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.4348. Min Act: -0.1700
Data Index: 5928947 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.4348. Min Act: -0.1700
Data Index: 8158795 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.4348. Min Act: -0.1700
Data Index: 5980116 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.4036. Min Act: -0.1700
Data Index: 1430341 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.3723. Min Act: -0.1700
Data Index: 3867351 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.3723. Min Act: -0.1700
Data Index: 1032575 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.3411. Min Act: -0.1700
Data Index: 8375848 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.3098. Min Act: -0.1700
Data Index: 5566846 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.2786. Min Act: -0.1700
Data Index: 759019 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.2786. Min Act: -0.1700
Data Index: 8640962 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.2473. Min Act: -0.1700
Data Index: 2265589 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.2161. Min Act: -0.1700
Data Index: 4053400 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.1536. Min Act: -0.1700
Data Index: 6787978 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.1536. Min Act: -0.1700
Data Index: 2566504 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.0911. Min Act: -0.1700
Data Index: 2547598 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.1536. Min Act: -0.1700
Data Index: 6101403 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7473. Min Range: -8.7473
Max Act: 8.1536. Min Act: -0.1700
Data Index: 8198076 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19