Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5091 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.1309. Min Range: -9.1309
Max Act: 9.1309. Min Act: -0.1700
Data Index: 2083705 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1309. Min Range: -9.1309
Max Act: 8.4434. Min Act: -0.1700
Data Index: 2481088 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1309. Min Range: -9.1309
Max Act: 8.3809. Min Act: -0.1700
Data Index: 6745732 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1309. Min Range: -9.1309
Max Act: 8.1309. Min Act: -0.1700
Data Index: 3697525 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.8809. Min Act: -0.1700
Data Index: 4589412 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.8184. Min Act: -0.1700
Data Index: 62287 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.7559. Min Act: -0.1700
Data Index: 2383203 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.7872. Min Act: -0.1700
Data Index: 4731045 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.7559. Min Act: -0.1700
Data Index: 4325832 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.6934. Min Act: -0.1700
Data Index: 670533 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.6934. Min Act: -0.1700
Data Index: 7742620 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.6622. Min Act: -0.1700
Data Index: 7207961 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.6309. Min Act: -0.1700
Data Index: 966850 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.5997. Min Act: -0.1700
Data Index: 5853510 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.5684. Min Act: -0.1700
Data Index: 5662117 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.5059. Min Act: -0.1700
Data Index: 5016385 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.4747. Min Act: -0.1700
Data Index: 5832041 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.5372. Min Act: -0.1700
Data Index: 8322158 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.5059. Min Act: -0.1700
Data Index: 5124213 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1309. Min Range: -9.1309
Max Act: 7.4434. Min Act: -0.1700
Data Index: 1474617 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19