Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2506 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2610. Min Range: -6.2610
Max Act: 6.2610. Min Act: -0.1700
Data Index: 5058991 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.8860. Min Act: -0.1700
Data Index: 8330020 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.8860. Min Act: -0.1700
Data Index: 8763527 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.7610. Min Act: -0.1700
Data Index: 8343477 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.5735. Min Act: -0.1700
Data Index: 8825268 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.5735. Min Act: -0.1700
Data Index: 3018979 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.5735. Min Act: -0.1700
Data Index: 5996975 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.6047. Min Act: -0.1700
Data Index: 770649 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.5422. Min Act: -0.1700
Data Index: 2625223 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4797. Min Act: -0.1700
Data Index: 2206868 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.5110. Min Act: -0.1700
Data Index: 8232779 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4485. Min Act: -0.1700
Data Index: 6027125 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4797. Min Act: -0.1700
Data Index: 439199 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4797. Min Act: -0.1700
Data Index: 625938 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4172. Min Act: -0.1700
Data Index: 3789274 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4485. Min Act: -0.1700
Data Index: 2250115 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4485. Min Act: -0.1700
Data Index: 1934866 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4485. Min Act: -0.1700
Data Index: 3136075 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4172. Min Act: -0.1700
Data Index: 5209700 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2610. Min Range: -6.2610
Max Act: 5.4172. Min Act: -0.1700
Data Index: 2933541 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19