Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.6724. Min Act: -0.1700
Data Index: 7428563 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.6376. Min Act: -0.1700
Data Index: 6704466 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.6202. Min Act: -0.1700
Data Index: 1952434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5765. Min Act: -0.1700
Data Index: 799874 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5765. Min Act: -0.1700
Data Index: 2488103 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5765. Min Act: -0.1693
Data Index: 8631934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5765. Min Act: -0.1699
Data Index: 933043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5853. Min Act: -0.1700
Data Index: 696984 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5678. Min Act: -0.1700
Data Index: 3376232 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5503. Min Act: -0.1700
Data Index: 3464223 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5503. Min Act: -0.1700
Data Index: 7142846 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5415. Min Act: -0.1700
Data Index: 4608164 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5415. Min Act: -0.1700
Data Index: 2488101 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5415. Min Act: -0.1700
Data Index: 6399 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5327. Min Act: -0.1700
Data Index: 5104381 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5415. Min Act: -0.1700
Data Index: 4055847 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5152. Min Act: -0.1700
Data Index: 2154957 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5240. Min Act: -0.1700
Data Index: 4147978 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5152. Min Act: -0.1700
Data Index: 861768 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6724. Min Range: -1.6724
Max Act: 1.5064. Min Act: -0.1700
Data Index: 3033235 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19