Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1828442 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.6514. Min Act: -0.1700
Data Index: 5802835 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.6514. Min Act: -0.1700
Data Index: 4920371 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.6674. Min Act: -0.1700
Data Index: 1691739 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.6031. Min Act: -0.1700
Data Index: 5196099 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5709. Min Act: -0.1700
Data Index: 3617456 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5870. Min Act: -0.1700
Data Index: 8680859 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5870. Min Act: -0.1700
Data Index: 7081651 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.6192. Min Act: -0.1700
Data Index: 2495749 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5870. Min Act: -0.1700
Data Index: 6261164 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5548. Min Act: -0.1700
Data Index: 3496104 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.6031. Min Act: -0.1700
Data Index: 6232757 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5548. Min Act: -0.1700
Data Index: 7156815 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5870. Min Act: -0.1700
Data Index: 7775803 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5386. Min Act: -0.1700
Data Index: 2431587 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5225. Min Act: -0.1700
Data Index: 8756533 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5063. Min Act: -0.1700
Data Index: 4292026 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.4739. Min Act: -0.1700
Data Index: 991705 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5386. Min Act: -0.1700
Data Index: 732121 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6834. Min Range: -2.6834
Max Act: 2.5225. Min Act: -0.1700
Data Index: 4875651 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19