Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9498. Min Act: -0.1700
Data Index: 6324866 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9656. Min Act: -0.1700
Data Index: 4299544 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9498. Min Act: -0.1700
Data Index: 6487704 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9339. Min Act: -0.1700
Data Index: 319225 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9339. Min Act: -0.1700
Data Index: 1592051 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9181. Min Act: -0.1700
Data Index: 8746382 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9023. Min Act: -0.1700
Data Index: 1380265 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9023. Min Act: -0.1700
Data Index: 6359995 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8864. Min Act: -0.1700
Data Index: 6450150 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8705. Min Act: -0.1700
Data Index: 7447248 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8864. Min Act: -0.1700
Data Index: 6359994 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.9023. Min Act: -0.1700
Data Index: 2264239 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8864. Min Act: -0.1700
Data Index: 5870865 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8546. Min Act: -0.1700
Data Index: 2006404 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8546. Min Act: -0.1700
Data Index: 8616536 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8705. Min Act: -0.1700
Data Index: 6911652 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8387. Min Act: -0.1700
Data Index: 136382 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8387. Min Act: -0.1700
Data Index: 8380024 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8546. Min Act: -0.1700
Data Index: 8808825 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9656. Min Range: -2.9656
Max Act: 2.8546. Min Act: -0.1700
Data Index: 2859675 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19