Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0681. Min Range: -9.0681
Max Act: 9.0681. Min Act: -0.1700
Data Index: 5977585 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.9431. Min Act: -0.1700
Data Index: 6952596 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0681. Min Range: -9.0681
Max Act: 9.0056. Min Act: -0.1700
Data Index: 6920580 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.9431. Min Act: -0.1700
Data Index: 2030106 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.9431. Min Act: -0.1700
Data Index: 2238686 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.8806. Min Act: -0.1700
Data Index: 2596099 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.8806. Min Act: -0.1700
Data Index: 3741047 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.8181. Min Act: -0.1700
Data Index: 4989465 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.7556. Min Act: -0.1700
Data Index: 3143754 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.8181. Min Act: -0.1700
Data Index: 2691319 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.6931. Min Act: -0.1700
Data Index: 8696381 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.6931. Min Act: -0.1700
Data Index: 6223730 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.6931. Min Act: -0.1700
Data Index: 3492539 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.6306. Min Act: -0.1700
Data Index: 1959493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.6931. Min Act: -0.1700
Data Index: 2492949 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.5681. Min Act: -0.1700
Data Index: 5536457 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.5056. Min Act: -0.1700
Data Index: 1953388 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.5056. Min Act: -0.1700
Data Index: 1383575 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.5056. Min Act: -0.1700
Data Index: 3384234 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0681. Min Range: -9.0681
Max Act: 8.5056. Min Act: -0.1700
Data Index: 4153454 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19