Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.2518. Min Act: -0.1700
Data Index: 6120823 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.1268. Min Act: -0.1700
Data Index: 2059949 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.0643. Min Act: -0.1700
Data Index: 2686266 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.0331. Min Act: -0.1700
Data Index: 7333909 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.0643. Min Act: -0.1700
Data Index: 5466374 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.0331. Min Act: -0.1700
Data Index: 6156422 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.0331. Min Act: -0.1700
Data Index: 5572013 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2518. Min Range: -5.2518
Max Act: 5.0018. Min Act: -0.1700
Data Index: 8828466 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9706. Min Act: -0.1700
Data Index: 1913451 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9081. Min Act: -0.1700
Data Index: 574890 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9393. Min Act: -0.1700
Data Index: 2020657 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9393. Min Act: -0.1700
Data Index: 3491126 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9081. Min Act: -0.1700
Data Index: 1387774 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4998156 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9081. Min Act: -0.1700
Data Index: 2477138 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9081. Min Act: -0.1700
Data Index: 2723253 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9081. Min Act: -0.1700
Data Index: 6748465 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9393. Min Act: -0.1700
Data Index: 1437589 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.8768. Min Act: -0.1700
Data Index: 228249 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2518. Min Range: -5.2518
Max Act: 4.9081. Min Act: -0.1700
Data Index: 7868566 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19