Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7976. Min Act: -0.1700
Data Index: 3301046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7976. Min Act: -0.1700
Data Index: 3515114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7663. Min Act: -0.1700
Data Index: 6735248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7663. Min Act: -0.1700
Data Index: 2161356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7351. Min Act: -0.1699
Data Index: 8461159 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7351. Min Act: -0.1700
Data Index: 1050208 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7351. Min Act: -0.1700
Data Index: 6126239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7351. Min Act: -0.1700
Data Index: 5496320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7351. Min Act: -0.1700
Data Index: 2067528 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7351. Min Act: -0.1700
Data Index: 3361117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.7351. Min Act: -0.1700
Data Index: 3349252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1700
Data Index: 3946476 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1700
Data Index: 2481174 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1700
Data Index: 4348864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1689
Data Index: 2528299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1700
Data Index: 70242 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1697
Data Index: 2189817 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1700
Data Index: 4629599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1691
Data Index: 6183712 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7976. Min Range: -5.7976
Max Act: 5.6726. Min Act: -0.1700
Data Index: 3107234 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19