Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.6307. Min Act: -0.1700
Data Index: 1090911 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.6307. Min Act: -0.1700
Data Index: 4210168 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.5057. Min Act: -0.1700
Data Index: 3789631 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.5057. Min Act: -0.1700
Data Index: 2162154 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.4432. Min Act: -0.1700
Data Index: 5614902 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.4432. Min Act: -0.1700
Data Index: 1978853 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.4432. Min Act: -0.1700
Data Index: 2339833 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.4119. Min Act: -0.1700
Data Index: 4093452 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.2557. Min Act: -0.1700
Data Index: 3410581 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.2244. Min Act: -0.1700
Data Index: 4360823 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.2244. Min Act: -0.1700
Data Index: 2138838 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.1932. Min Act: -0.1700
Data Index: 5349696 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.1932. Min Act: -0.1700
Data Index: 1917525 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.1619. Min Act: -0.1700
Data Index: 3348097 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.1307. Min Act: -0.1700
Data Index: 4670396 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4722144 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0994. Min Act: -0.1700
Data Index: 4828469 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0682. Min Act: -0.1700
Data Index: 7663144 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0682. Min Act: -0.1700
Data Index: 2948922 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0682. Min Act: -0.1700
Data Index: 188665 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19