Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4894 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6950. Min Act: -0.1700
Data Index: 2814052 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6950. Min Act: -0.1700
Data Index: 2628866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6950. Min Act: -0.1700
Data Index: 7716499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6950. Min Act: -0.1700
Data Index: 1470790 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6950. Min Act: -0.1700
Data Index: 6389744 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6637. Min Act: -0.1700
Data Index: 8468117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 6795322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6637. Min Act: -0.1700
Data Index: 2510270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6637. Min Act: -0.1700
Data Index: 2425698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6637. Min Act: -0.1700
Data Index: 5822770 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1697
Data Index: 3386951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6637. Min Act: -0.1700
Data Index: 7771008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 1300601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 3590762 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 7058226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 7708667 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 124045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 5553600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 4291347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6950. Min Range: -3.6950
Max Act: 3.6324. Min Act: -0.1700
Data Index: 174800 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19