Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.4116. Min Act: -0.1700
Data Index: 7877685 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.2554. Min Act: -0.1700
Data Index: 4014079 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.1929. Min Act: -0.1700
Data Index: 4014080 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0991. Min Act: -0.1700
Data Index: 13551 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.1304. Min Act: -0.1700
Data Index: 7004316 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0991. Min Act: -0.1700
Data Index: 1099719 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.1304. Min Act: -0.1700
Data Index: 6790021 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0991. Min Act: -0.1700
Data Index: 7936106 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0679. Min Act: -0.1700
Data Index: 5582550 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0679. Min Act: -0.1700
Data Index: 5420744 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0366. Min Act: -0.1700
Data Index: 6870977 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0366. Min Act: -0.1700
Data Index: 2691135 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0679. Min Act: -0.1700
Data Index: 5495053 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0366. Min Act: -0.1700
Data Index: 7341679 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4116. Min Range: -6.4116
Max Act: 5.9741. Min Act: -0.1700
Data Index: 4591839 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4116. Min Range: -6.4116
Max Act: 5.9741. Min Act: -0.1700
Data Index: 6837505 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4116. Min Range: -6.4116
Max Act: 5.9741. Min Act: -0.1700
Data Index: 1228516 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4116. Min Range: -6.4116
Max Act: 5.9429. Min Act: -0.1700
Data Index: 5289251 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4116. Min Range: -6.4116
Max Act: 5.9429. Min Act: -0.1700
Data Index: 2220192 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4116. Min Range: -6.4116
Max Act: 6.0054. Min Act: -0.1700
Data Index: 3540453 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19