Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3912 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0181. Min Range: -7.0181
Max Act: 7.0181. Min Act: -0.1700
Data Index: 8392664 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.5494. Min Act: -0.1700
Data Index: 3865249 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.5181. Min Act: -0.1700
Data Index: 6148986 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.3931. Min Act: -0.1700
Data Index: 5197065 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.3306. Min Act: -0.1700
Data Index: 6062930 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.3619. Min Act: -0.1700
Data Index: 5972797 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.3306. Min Act: -0.1700
Data Index: 4415349 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2681. Min Act: -0.1700
Data Index: 6324564 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2994. Min Act: -0.1700
Data Index: 1176008 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2369. Min Act: -0.1700
Data Index: 3008891 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2369. Min Act: -0.1700
Data Index: 7391926 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2056. Min Act: -0.1700
Data Index: 1264036 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2056. Min Act: -0.1700
Data Index: 7696506 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2056. Min Act: -0.1700
Data Index: 351904 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2056. Min Act: -0.1700
Data Index: 6387973 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.2056. Min Act: -0.1700
Data Index: 2115007 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.1119. Min Act: -0.1700
Data Index: 2841613 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.0806. Min Act: -0.1700
Data Index: 3990997 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.1431. Min Act: -0.1700
Data Index: 8477749 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0181. Min Range: -7.0181
Max Act: 6.1431. Min Act: -0.1700
Data Index: 7985440 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19