Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2561 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7538. Min Act: -0.1700
Data Index: 2777384 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7538. Min Act: -0.1700
Data Index: 4562187 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.6600. Min Act: -0.1700
Data Index: 1088131 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5663. Min Act: -0.1700
Data Index: 2387565 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5663. Min Act: -0.1700
Data Index: 93214 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 5677348 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 546699 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 3247881 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 5756308 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4924251 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 2139629 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 406383 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 8188539 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6773340 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 700054 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 3036075 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6724427 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 2623390 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6156248 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4725. Min Act: -0.1700
Data Index: 5555285 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19