Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2349 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 79812 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 6178780 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0346. Min Act: -0.1700
Data Index: 7351716 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 7351714 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 2527426 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4977356 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4977354 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9720. Min Act: -0.1700
Data Index: 8277982 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 2206024 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9408. Min Act: -0.1700
Data Index: 6578851 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4129221 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9408. Min Act: -0.1700
Data Index: 4129223 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9720. Min Act: -0.1700
Data Index: 3473338 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9720. Min Act: -0.1700
Data Index: 3473340 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9408. Min Act: -0.1700
Data Index: 7037326 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0346. Min Range: -5.0346
Max Act: 5.0033. Min Act: -0.1700
Data Index: 6578849 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9720. Min Act: -0.1700
Data Index: 5622974 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9720. Min Act: -0.1700
Data Index: 4839152 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9720. Min Act: -0.1700
Data Index: 4839150 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0346. Min Range: -5.0346
Max Act: 4.9720. Min Act: -0.1700
Data Index: 4414280 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19