Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0739. Min Act: -0.1700
Data Index: 3027878 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0739. Min Act: -0.1700
Data Index: 6316281 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9802. Min Act: -0.1700
Data Index: 1823873 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 2478690 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 2922433 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8552. Min Act: -0.1700
Data Index: 5695456 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8239. Min Act: -0.1700
Data Index: 2585898 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8239. Min Act: -0.1700
Data Index: 5442227 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8239. Min Act: -0.1700
Data Index: 2911092 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 6830090 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7927. Min Act: -0.1700
Data Index: 8297134 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8239. Min Act: -0.1700
Data Index: 6243626 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7927. Min Act: -0.1700
Data Index: 6131653 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 3485171 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1356647 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1957830 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 1787174 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 5339131 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7302. Min Act: -0.1700
Data Index: 4669621 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7302. Min Act: -0.1700
Data Index: 2870572 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19