Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1004. Min Range: -3.1004
Max Act: 3.1004. Min Act: -0.1700
Data Index: 4887806 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1004. Min Range: -3.1004
Max Act: 3.0215. Min Act: -0.1700
Data Index: 3274261 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1004. Min Range: -3.1004
Max Act: 3.0373. Min Act: -0.1700
Data Index: 1344757 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1004. Min Range: -3.1004
Max Act: 3.0215. Min Act: -0.1700
Data Index: 932152 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9899. Min Act: -0.1700
Data Index: 5576445 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9583. Min Act: -0.1700
Data Index: 865312 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1004. Min Range: -3.1004
Max Act: 3.0057. Min Act: -0.1700
Data Index: 5537376 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9583. Min Act: -0.1700
Data Index: 7291537 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9425. Min Act: -0.1700
Data Index: 2359973 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9583. Min Act: -0.1700
Data Index: 7348005 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.8790. Min Act: -0.1700
Data Index: 4682876 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9266. Min Act: -0.1700
Data Index: 1325826 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9266. Min Act: -0.1700
Data Index: 2610041 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9108. Min Act: -0.1700
Data Index: 4362154 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9108. Min Act: -0.1700
Data Index: 6200567 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9425. Min Act: -0.1700
Data Index: 1172083 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9741. Min Act: -0.1700
Data Index: 3622922 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9741. Min Act: -0.1700
Data Index: 1408932 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9108. Min Act: -0.1700
Data Index: 2558808 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1004. Min Range: -3.1004
Max Act: 2.9266. Min Act: -0.1700
Data Index: 3705702 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19