Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1133 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.8898. Min Act: -0.1700
Data Index: 8613441 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.7961. Min Act: -0.1700
Data Index: 7657944 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.4836. Min Act: -0.1700
Data Index: 7791200 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.4836. Min Act: -0.1700
Data Index: 8010855 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.4211. Min Act: -0.1700
Data Index: 7408057 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3898. Min Act: -0.1700
Data Index: 1833976 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.3586. Min Act: -0.1700
Data Index: 7161070 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.2961. Min Act: -0.1700
Data Index: 8457624 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.2961. Min Act: -0.1700
Data Index: 999399 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.2648. Min Act: -0.1700
Data Index: 8315566 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.2336. Min Act: -0.1700
Data Index: 5446987 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.2648. Min Act: -0.1700
Data Index: 6164379 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.2336. Min Act: -0.1700
Data Index: 2183744 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.2336. Min Act: -0.1700
Data Index: 4357655 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.1711. Min Act: -0.1700
Data Index: 2069840 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.1398. Min Act: -0.1700
Data Index: 4501013 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.1711. Min Act: -0.1700
Data Index: 2196312 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.1711. Min Act: -0.1700
Data Index: 5871837 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.1398. Min Act: -0.1700
Data Index: 2105280 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8898. Min Range: -6.8898
Max Act: 6.1086. Min Act: -0.1700
Data Index: 7318896 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19