Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4475 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.9491. Min Act: -0.1700
Data Index: 1039229 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8554. Min Act: -0.1700
Data Index: 640773 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.7929. Min Act: -0.1700
Data Index: 4603422 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6679. Min Act: -0.1700
Data Index: 3696251 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 914053 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6366. Min Act: -0.1700
Data Index: 1080512 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.5429. Min Act: -0.1700
Data Index: 8610951 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.4804. Min Act: -0.1700
Data Index: 7012306 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.5429. Min Act: -0.1700
Data Index: 4951607 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.4491. Min Act: -0.1700
Data Index: 2893433 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.4804. Min Act: -0.1700
Data Index: 3751084 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.4491. Min Act: -0.1700
Data Index: 8805472 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.4179. Min Act: -0.1700
Data Index: 3538888 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.3866. Min Act: -0.1700
Data Index: 5416457 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.3554. Min Act: -0.1700
Data Index: 273170 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.3554. Min Act: -0.1700
Data Index: 3135515 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.2929. Min Act: -0.1700
Data Index: 8758526 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.2929. Min Act: -0.1700
Data Index: 1273891 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.2929. Min Act: -0.1700
Data Index: 2407392 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.2616. Min Act: -0.1700
Data Index: 5819651 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19