Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.7317. Min Act: -0.1700
Data Index: 6609243 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.5754. Min Act: -0.1700
Data Index: 8520047 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.5129. Min Act: -0.1700
Data Index: 8475001 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.4504. Min Act: -0.1700
Data Index: 2330945 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.4192. Min Act: -0.1700
Data Index: 56994 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3567. Min Act: -0.1700
Data Index: 8123611 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3553667 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3879. Min Act: -0.1700
Data Index: 4126665 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3879. Min Act: -0.1700
Data Index: 8485261 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.4192. Min Act: -0.1700
Data Index: 8162246 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3254. Min Act: -0.1700
Data Index: 8616586 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3567. Min Act: -0.1700
Data Index: 6340285 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3254. Min Act: -0.1700
Data Index: 1386251 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3254. Min Act: -0.1700
Data Index: 472473 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3254. Min Act: -0.1700
Data Index: 464589 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.3254. Min Act: -0.1700
Data Index: 3571336 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.2629. Min Act: -0.1700
Data Index: 7986438 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.2629. Min Act: -0.1700
Data Index: 6525022 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.2317. Min Act: -0.1700
Data Index: 1944490 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7317. Min Range: -5.7317
Max Act: 5.2629. Min Act: -0.1700
Data Index: 8441923 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19