Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.8396. Min Act: -0.1700
Data Index: 8023466 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.3709. Min Act: -0.1700
Data Index: 1524709 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.2771. Min Act: -0.1700
Data Index: 1672740 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.2771. Min Act: -0.1700
Data Index: 2526035 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.1521. Min Act: -0.1700
Data Index: 147083 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.1834. Min Act: -0.1700
Data Index: 3079576 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0896. Min Act: -0.1700
Data Index: 8095196 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.1209. Min Act: -0.1700
Data Index: 2508708 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0896. Min Act: -0.1700
Data Index: 4213161 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0896. Min Act: -0.1700
Data Index: 6839972 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0896. Min Act: -0.1700
Data Index: 4590082 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0271. Min Act: -0.1700
Data Index: 3025846 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0584. Min Act: -0.1700
Data Index: 3557443 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0271. Min Act: -0.1700
Data Index: 5093705 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8396. Min Range: -5.8396
Max Act: 4.9959. Min Act: -0.1700
Data Index: 6656213 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8396. Min Range: -5.8396
Max Act: 4.9646. Min Act: -0.1700
Data Index: 2549827 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8396. Min Range: -5.8396
Max Act: 4.9959. Min Act: -0.1700
Data Index: 1802114 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8396. Min Range: -5.8396
Max Act: 5.0271. Min Act: -0.1700
Data Index: 4194893 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8396. Min Range: -5.8396
Max Act: 4.9646. Min Act: -0.1700
Data Index: 3529009 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8396. Min Range: -5.8396
Max Act: 4.9646. Min Act: -0.1700
Data Index: 6556448 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19