Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1113 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.3816. Min Act: -0.1700
Data Index: 6835942 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.3191. Min Act: -0.1700
Data Index: 3113572 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.2254. Min Act: -0.1700
Data Index: 8372037 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.0691. Min Act: -0.1700
Data Index: 6555989 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1316. Min Act: -0.1700
Data Index: 4835105 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.0691. Min Act: -0.1700
Data Index: 5659898 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.0691. Min Act: -0.1700
Data Index: 6958259 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.0691. Min Act: -0.1700
Data Index: 6144519 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.0066. Min Act: -0.1700
Data Index: 3331112 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9754. Min Act: -0.1700
Data Index: 4198615 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9441. Min Act: -0.1700
Data Index: 4127492 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.0066. Min Act: -0.1700
Data Index: 5651662 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9754. Min Act: -0.1700
Data Index: 4115431 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9754. Min Act: -0.1700
Data Index: 5651655 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9441. Min Act: -0.1700
Data Index: 1147129 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9129. Min Act: -0.1700
Data Index: 739898 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9441. Min Act: -0.1700
Data Index: 5417392 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9441. Min Act: -0.1700
Data Index: 902885 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9441. Min Act: -0.1700
Data Index: 5811976 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3816. Min Range: -5.3816
Max Act: 4.9129. Min Act: -0.1700
Data Index: 4861340 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19