Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 85 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.5637. Min Act: -0.1700
Data Index: 2016793 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.3137. Min Act: -0.1700
Data Index: 6261849 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.3137. Min Act: -0.1700
Data Index: 6848887 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.2512. Min Act: -0.1700
Data Index: 22729 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.2512. Min Act: -0.1700
Data Index: 6720427 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.2512. Min Act: -0.1700
Data Index: 1573873 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.2200. Min Act: -0.1700
Data Index: 1216558 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1262. Min Act: -0.1700
Data Index: 6538651 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1262. Min Act: -0.1700
Data Index: 7719083 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1887. Min Act: -0.1700
Data Index: 7924662 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1575. Min Act: -0.1700
Data Index: 4231673 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.0950. Min Act: -0.1700
Data Index: 5550034 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1262. Min Act: -0.1700
Data Index: 2739623 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1262. Min Act: -0.1700
Data Index: 5761827 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1262. Min Act: -0.1700
Data Index: 4563830 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.1262. Min Act: -0.1700
Data Index: 1669485 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.0637. Min Act: -0.1700
Data Index: 1516644 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.0637. Min Act: -0.1700
Data Index: 773526 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.0637. Min Act: -0.1700
Data Index: 6195864 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5637. Min Range: -5.5637
Max Act: 5.0637. Min Act: -0.1700
Data Index: 4592048 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19