Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3651 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.3296. Min Act: -0.1700
Data Index: 4298484 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.3296. Min Act: -0.1700
Data Index: 847876 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.2984. Min Act: -0.1700
Data Index: 5671260 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.1734. Min Act: -0.1700
Data Index: 783732 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.0796. Min Act: -0.1700
Data Index: 1532373 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.0796. Min Act: -0.1700
Data Index: 3410502 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.0796. Min Act: -0.1700
Data Index: 733852 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.0484. Min Act: -0.1700
Data Index: 8446170 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3296. Min Range: -6.3296
Max Act: 6.0171. Min Act: -0.1700
Data Index: 3144260 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9859. Min Act: -0.1700
Data Index: 7603159 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9859. Min Act: -0.1700
Data Index: 7615571 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9546. Min Act: -0.1700
Data Index: 509617 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9859. Min Act: -0.1698
Data Index: 3042392 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9546. Min Act: -0.1700
Data Index: 1120521 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9546. Min Act: -0.1700
Data Index: 1534788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9546. Min Act: -0.1700
Data Index: 5472347 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9546. Min Act: -0.1700
Data Index: 5429297 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9546. Min Act: -0.1700
Data Index: 4182966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9859. Min Act: -0.1700
Data Index: 4829532 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3296. Min Range: -6.3296
Max Act: 5.9546. Min Act: -0.1700
Data Index: 1920724 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19