Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.3537. Min Act: -0.1700
Data Index: 5721000 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.2599. Min Act: -0.1700
Data Index: 2344975 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.2287. Min Act: -0.1700
Data Index: 1627278 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.1662. Min Act: -0.1700
Data Index: 4464300 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.1662. Min Act: -0.1700
Data Index: 8012306 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.1037. Min Act: -0.1700
Data Index: 8465142 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.0724. Min Act: -0.1695
Data Index: 2687139 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.0099. Min Act: -0.1700
Data Index: 817206 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3537. Min Range: -4.3537
Max Act: 4.0099. Min Act: -0.1684
Data Index: 903938 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9786. Min Act: -0.1700
Data Index: 6596255 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9786. Min Act: -0.1700
Data Index: 5382800 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9786. Min Act: -0.1700
Data Index: 1420653 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9786. Min Act: -0.1700
Data Index: 5151987 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9474. Min Act: -0.1700
Data Index: 7654357 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9474. Min Act: -0.1700
Data Index: 8322166 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9474. Min Act: -0.1700
Data Index: 3425511 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9474. Min Act: -0.1700
Data Index: 8292385 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9474. Min Act: -0.1700
Data Index: 4961281 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9474. Min Act: -0.1700
Data Index: 5482209 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3537. Min Range: -4.3537
Max Act: 3.9474. Min Act: -0.1700
Data Index: 3499667 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19