Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.6394. Min Act: -0.1700
Data Index: 2260142 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.6707. Min Act: -0.1700
Data Index: 17744 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.6082. Min Act: -0.1700
Data Index: 5478158 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.4519. Min Act: -0.1700
Data Index: 2778834 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.4519. Min Act: -0.1700
Data Index: 112400 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7601309 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.4207. Min Act: -0.1700
Data Index: 8719329 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.3269. Min Act: -0.1700
Data Index: 2013551 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.3894. Min Act: -0.1700
Data Index: 7492402 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.3269. Min Act: -0.1700
Data Index: 7591814 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2644. Min Act: -0.1700
Data Index: 55881 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2957. Min Act: -0.1700
Data Index: 4359113 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2957. Min Act: -0.1700
Data Index: 87917 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2644. Min Act: -0.1700
Data Index: 7321920 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2332. Min Act: -0.1700
Data Index: 8069610 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2644. Min Act: -0.1700
Data Index: 1316975 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2332. Min Act: -0.1700
Data Index: 2629398 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2332. Min Act: -0.1700
Data Index: 7699159 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2332. Min Act: -0.1700
Data Index: 5296375 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6707. Min Range: -5.6707
Max Act: 5.2019. Min Act: -0.1700
Data Index: 4895806 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19