Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4533. Min Range: -6.4533
Max Act: 6.4533. Min Act: -0.1700
Data Index: 503582 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4533. Min Range: -6.4533
Max Act: 6.2971. Min Act: -0.1700
Data Index: 876447 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4533. Min Range: -6.4533
Max Act: 6.0158. Min Act: -0.1700
Data Index: 8499641 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.9221. Min Act: -0.1700
Data Index: 2407721 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.8283. Min Act: -0.1700
Data Index: 2386283 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.7658. Min Act: -0.1700
Data Index: 6978514 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.7346. Min Act: -0.1700
Data Index: 1595308 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.7033. Min Act: -0.1700
Data Index: 3042927 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.6408. Min Act: -0.1700
Data Index: 8594838 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.6096. Min Act: -0.1700
Data Index: 7830067 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5783. Min Act: -0.1700
Data Index: 7285908 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5783. Min Act: -0.1700
Data Index: 31334 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5471. Min Act: -0.1700
Data Index: 3173677 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5471. Min Act: -0.1700
Data Index: 1603062 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5471. Min Act: -0.1700
Data Index: 4717377 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5471. Min Act: -0.1700
Data Index: 6400851 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5783. Min Act: -0.1700
Data Index: 730826 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5158. Min Act: -0.1700
Data Index: 8807193 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.5158. Min Act: -0.1700
Data Index: 5877090 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4533. Min Range: -6.4533
Max Act: 5.4846. Min Act: -0.1700
Data Index: 2754910 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19