Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.5858. Min Act: -0.1700
Data Index: 3698382 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.3983. Min Act: -0.1700
Data Index: 4486643 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.3983. Min Act: -0.1700
Data Index: 6636673 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.2733. Min Act: -0.1700
Data Index: 8361097 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.2421. Min Act: -0.1700
Data Index: 751475 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.2108. Min Act: -0.1700
Data Index: 2022419 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.1171. Min Act: -0.1700
Data Index: 3558672 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.1171. Min Act: -0.1700
Data Index: 8126754 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.1171. Min Act: -0.1700
Data Index: 5426069 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.1171. Min Act: -0.1700
Data Index: 1326339 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.1171. Min Act: -0.1700
Data Index: 8693158 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.0858. Min Act: -0.1700
Data Index: 1326343 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.0546. Min Act: -0.1700
Data Index: 267639 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.0546. Min Act: -0.1700
Data Index: 457643 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.0546. Min Act: -0.1700
Data Index: 3599308 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5858. Min Range: -7.5858
Max Act: 7.0233. Min Act: -0.1700
Data Index: 1992444 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5858. Min Range: -7.5858
Max Act: 6.9921. Min Act: -0.1700
Data Index: 5772021 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5858. Min Range: -7.5858
Max Act: 6.9608. Min Act: -0.1700
Data Index: 2062158 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5858. Min Range: -7.5858
Max Act: 6.9608. Min Act: -0.1700
Data Index: 8087130 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5858. Min Range: -7.5858
Max Act: 6.9608. Min Act: -0.1700
Data Index: 1326338 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19