Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3894 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.3684. Min Act: -0.1700
Data Index: 3359337 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.3372. Min Act: -0.1700
Data Index: 8751898 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.2747. Min Act: -0.1700
Data Index: 3825739 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.2434. Min Act: -0.1700
Data Index: 5424078 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.2434. Min Act: -0.1700
Data Index: 3244121 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.2122. Min Act: -0.1700
Data Index: 6171143 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.2122. Min Act: -0.1700
Data Index: 8611197 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.2122. Min Act: -0.1700
Data Index: 8274669 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.2122. Min Act: -0.1700
Data Index: 5629915 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1809. Min Act: -0.1700
Data Index: 6872751 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1809. Min Act: -0.1700
Data Index: 5430164 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1809. Min Act: -0.1700
Data Index: 2336992 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1497. Min Act: -0.1700
Data Index: 2246473 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1497. Min Act: -0.1700
Data Index: 8454016 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1497. Min Act: -0.1700
Data Index: 374651 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1497. Min Act: -0.1700
Data Index: 5274301 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1809. Min Act: -0.1700
Data Index: 119974 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1184. Min Act: -0.1700
Data Index: 5089656 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1184. Min Act: -0.1700
Data Index: 6423294 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3684. Min Range: -4.3684
Max Act: 4.1184. Min Act: -0.1700
Data Index: 3692071 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19