Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1002 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2173. Min Range: -11.2173
Max Act: 11.2173. Min Act: -0.1700
Data Index: 8580553 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.8423. Min Act: -0.1700
Data Index: 6496906 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.6548. Min Act: -0.1700
Data Index: 1213839 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.6548. Min Act: -0.1700
Data Index: 5614471 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.5298. Min Act: -0.1700
Data Index: 51588 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.4048. Min Act: -0.1700
Data Index: 2928856 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.3423. Min Act: -0.1700
Data Index: 7227521 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.3423. Min Act: -0.1700
Data Index: 7536360 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.3423. Min Act: -0.1700
Data Index: 7935464 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.2798. Min Act: -0.1700
Data Index: 8565712 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.2173. Min Act: -0.1700
Data Index: 4136118 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.1548. Min Act: -0.1699
Data Index: 850368 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.1548. Min Act: -0.1700
Data Index: 6050725 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.0298. Min Act: -0.1700
Data Index: 2866468 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.0298. Min Act: -0.1700
Data Index: 6790157 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.0923. Min Act: -0.1700
Data Index: 6020637 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2173. Min Range: -11.2173
Max Act: 10.0298. Min Act: -0.1700
Data Index: 2487189 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2173. Min Range: -11.2173
Max Act: 9.9673. Min Act: -0.1700
Data Index: 5713598 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2173. Min Range: -11.2173
Max Act: 9.9673. Min Act: -0.1700
Data Index: 5013321 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2173. Min Range: -11.2173
Max Act: 9.9673. Min Act: -0.1696
Data Index: 7273390 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19