Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.9910. Min Act: -0.1700
Data Index: 4078458 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.9910. Min Act: -0.1700
Data Index: 4716260 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.9910. Min Act: -0.1700
Data Index: 2033959 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.9598. Min Act: -0.1700
Data Index: 6108092 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.9598. Min Act: -0.1700
Data Index: 3938692 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.9285. Min Act: -0.1700
Data Index: 7398973 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8972. Min Act: -0.1700
Data Index: 3167948 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8972. Min Act: -0.1700
Data Index: 3081463 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8816. Min Act: -0.1700
Data Index: 638126 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8816. Min Act: -0.1700
Data Index: 7402764 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8660. Min Act: -0.1700
Data Index: 8369010 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8503. Min Act: -0.1700
Data Index: 3167946 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8503. Min Act: -0.1700
Data Index: 3622479 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8347. Min Act: -0.1700
Data Index: 5416274 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8503. Min Act: -0.1700
Data Index: 3167945 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8503. Min Act: -0.1700
Data Index: 6716581 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8347. Min Act: -0.1700
Data Index: 3167947 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8347. Min Act: -0.1700
Data Index: 3439353 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8034. Min Act: -0.1700
Data Index: 5145709 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9910. Min Range: -3.9910
Max Act: 3.8347. Min Act: -0.1700
Data Index: 7251714 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19