Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.9354. Min Act: -0.1700
Data Index: 2480304 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.8729. Min Act: -0.1700
Data Index: 8164543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.8104. Min Act: -0.1700
Data Index: 5490029 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.8104. Min Act: -0.1700
Data Index: 5276831 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.7479. Min Act: -0.1700
Data Index: 5700313 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.7479. Min Act: -0.1700
Data Index: 7969793 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.7479. Min Act: -0.1699
Data Index: 8470471 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.7479. Min Act: -0.1700
Data Index: 177526 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.7479. Min Act: -0.1700
Data Index: 4382288 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.7479. Min Act: -0.1700
Data Index: 4090529 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.7479. Min Act: -0.1700
Data Index: 4038615 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6854. Min Act: -0.1700
Data Index: 4592126 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6854. Min Act: -0.1700
Data Index: 4234036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6854. Min Act: -0.1700
Data Index: 3958132 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6854. Min Act: -0.1700
Data Index: 3797087 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6229. Min Act: -0.1700
Data Index: 3675855 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6854. Min Act: -0.1700
Data Index: 3440738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6854. Min Act: -0.1700
Data Index: 3407777 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6854. Min Act: -0.1700
Data Index: 325794 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9354. Min Range: -6.9354
Max Act: 6.6229. Min Act: -0.1700
Data Index: 2801989 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19