Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.4451. Min Act: -0.1700
Data Index: 2339835 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.3201. Min Act: -0.1700
Data Index: 6020234 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.3201. Min Act: -0.1700
Data Index: 4361872 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.2264. Min Act: -0.1700
Data Index: 1579840 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.1951. Min Act: -0.1700
Data Index: 3298051 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.1326. Min Act: -0.1700
Data Index: 7734738 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.0701. Min Act: -0.1700
Data Index: 4408197 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.0701. Min Act: -0.1700
Data Index: 6857222 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.0389. Min Act: -0.1700
Data Index: 6286068 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4451. Min Range: -8.4451
Max Act: 8.0076. Min Act: -0.1700
Data Index: 5028449 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.8514. Min Act: -0.1700
Data Index: 5162289 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.7889. Min Act: -0.1700
Data Index: 4108217 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.8201. Min Act: -0.1700
Data Index: 7085906 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.8201. Min Act: -0.1700
Data Index: 8576778 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.7889. Min Act: -0.1700
Data Index: 365238 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.7264. Min Act: -0.1700
Data Index: 3602677 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.7264. Min Act: -0.1700
Data Index: 2662537 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.7264. Min Act: -0.1700
Data Index: 1919508 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.6639. Min Act: -0.1700
Data Index: 3237581 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4451. Min Range: -8.4451
Max Act: 7.7264. Min Act: -0.1700
Data Index: 2915350 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19