Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 361 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.6951. Min Act: -0.1700
Data Index: 2326269 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.6639. Min Act: -0.1700
Data Index: 8673483 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.6014. Min Act: -0.1700
Data Index: 1842002 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.5389. Min Act: -0.1700
Data Index: 3433600 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.6014. Min Act: -0.1700
Data Index: 5633115 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.5076. Min Act: -0.1700
Data Index: 796884 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.5389. Min Act: -0.1700
Data Index: 8328655 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.5076. Min Act: -0.1700
Data Index: 6674360 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.5076. Min Act: -0.1700
Data Index: 812937 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4764. Min Act: -0.1700
Data Index: 2282345 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4451. Min Act: -0.1700
Data Index: 586912 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4764. Min Act: -0.1700
Data Index: 7876002 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4451. Min Act: -0.1700
Data Index: 4164832 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4139. Min Act: -0.1700
Data Index: 1659495 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4451. Min Act: -0.1700
Data Index: 3297119 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4451. Min Act: -0.1700
Data Index: 6075306 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4139. Min Act: -0.1700
Data Index: 2466050 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4139. Min Act: -0.1700
Data Index: 658488 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4139. Min Act: -0.1700
Data Index: 7521937 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6951. Min Range: -5.6951
Max Act: 5.4139. Min Act: -0.1700
Data Index: 308567 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19