Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.7309. Min Act: -0.1700
Data Index: 8052145 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.3872. Min Act: -0.1700
Data Index: 1053467 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.1997. Min Act: -0.1700
Data Index: 3813237 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.1684. Min Act: -0.1700
Data Index: 4771102 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.1997. Min Act: -0.1700
Data Index: 4897123 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.1059. Min Act: -0.1700
Data Index: 2751078 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 1939661 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 7356569 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 7407032 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 8823000 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.0747. Min Act: -0.1700
Data Index: 1732301 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.0122. Min Act: -0.1700
Data Index: 3329916 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7309. Min Range: -5.7309
Max Act: 5.0122. Min Act: -0.1700
Data Index: 2428233 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7309. Min Range: -5.7309
Max Act: 4.9497. Min Act: -0.1700
Data Index: 4042554 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7309. Min Range: -5.7309
Max Act: 4.9809. Min Act: -0.1700
Data Index: 3147501 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7309. Min Range: -5.7309
Max Act: 4.9809. Min Act: -0.1700
Data Index: 1732291 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7309. Min Range: -5.7309
Max Act: 4.9809. Min Act: -0.1700
Data Index: 726579 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7309. Min Range: -5.7309
Max Act: 4.9497. Min Act: -0.1700
Data Index: 3141680 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7309. Min Range: -5.7309
Max Act: 4.9184. Min Act: -0.1700
Data Index: 2551814 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7309. Min Range: -5.7309
Max Act: 4.9497. Min Act: -0.1700
Data Index: 5936014 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19