Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.5908. Min Act: -0.1700
Data Index: 2315328 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.5596. Min Act: -0.1700
Data Index: 6307180 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.5596. Min Act: -0.1700
Data Index: 7252482 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.5596. Min Act: -0.1700
Data Index: 8806237 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.4658. Min Act: -0.1700
Data Index: 6175694 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.3408. Min Act: -0.1700
Data Index: 7263423 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.2783. Min Act: -0.1700
Data Index: 4209117 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.2471. Min Act: -0.1700
Data Index: 4325760 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.2471. Min Act: -0.1700
Data Index: 6011181 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.2158. Min Act: -0.1700
Data Index: 929837 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1846. Min Act: -0.1700
Data Index: 6252555 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1846. Min Act: -0.1700
Data Index: 2019468 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1533. Min Act: -0.1700
Data Index: 8343054 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1533. Min Act: -0.1700
Data Index: 5224613 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1533. Min Act: -0.1700
Data Index: 1217458 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1533. Min Act: -0.1700
Data Index: 7492449 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1533. Min Act: -0.1700
Data Index: 3616932 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.1221. Min Act: -0.1700
Data Index: 2509813 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.0908. Min Act: -0.1700
Data Index: 1104756 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5908. Min Range: -6.5908
Max Act: 6.0908. Min Act: -0.1700
Data Index: 4193575 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19