Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0584. Min Range: -6.0584
Max Act: 6.0584. Min Act: -0.1700
Data Index: 7518405 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0584. Min Range: -6.0584
Max Act: 6.0271. Min Act: -0.1700
Data Index: 3012026 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.9646. Min Act: -0.1700
Data Index: 3654352 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.8709. Min Act: -0.1700
Data Index: 4446809 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.8396. Min Act: -0.1700
Data Index: 308580 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.8084. Min Act: -0.1700
Data Index: 488568 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.8084. Min Act: -0.1700
Data Index: 5764769 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.7771. Min Act: -0.1700
Data Index: 1240179 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.7771. Min Act: -0.1700
Data Index: 3111209 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.7771. Min Act: -0.1700
Data Index: 6289445 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.7459. Min Act: -0.1700
Data Index: 7355649 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.7146. Min Act: -0.1700
Data Index: 7639653 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.7146. Min Act: -0.1700
Data Index: 7972413 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.6834. Min Act: -0.1700
Data Index: 8211318 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.7146. Min Act: -0.1700
Data Index: 8076103 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.6521. Min Act: -0.1700
Data Index: 5979718 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.6521. Min Act: -0.1700
Data Index: 1856705 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.6209. Min Act: -0.1700
Data Index: 4467061 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.6209. Min Act: -0.1700
Data Index: 3562412 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0584. Min Range: -6.0584
Max Act: 5.6209. Min Act: -0.1700
Data Index: 3351330 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19