Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.8851. Min Act: -0.1700
Data Index: 2610802 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.6351. Min Act: -0.1700
Data Index: 41099 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.5101. Min Act: -0.1700
Data Index: 5670422 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.4788. Min Act: -0.1700
Data Index: 8526206 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.3851. Min Act: -0.1700
Data Index: 5706481 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.3538. Min Act: -0.1700
Data Index: 6111137 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.3226. Min Act: -0.1700
Data Index: 2026245 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.3538. Min Act: -0.1700
Data Index: 2846467 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.2913. Min Act: -0.1700
Data Index: 8531392 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.2913. Min Act: -0.1700
Data Index: 8759700 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.2913. Min Act: -0.1700
Data Index: 856604 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.3226. Min Act: -0.1700
Data Index: 106828 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1663. Min Act: -0.1700
Data Index: 3900512 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1976. Min Act: -0.1700
Data Index: 265993 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1976. Min Act: -0.1700
Data Index: 6069882 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1663. Min Act: -0.1700
Data Index: 8128717 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1663. Min Act: -0.1700
Data Index: 6722086 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1663. Min Act: -0.1700
Data Index: 4722486 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1351. Min Act: -0.1700
Data Index: 4052067 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8851. Min Range: -6.8851
Max Act: 6.1038. Min Act: -0.1700
Data Index: 5821529 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19