Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.3104. Min Act: -0.1700
Data Index: 7798537 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.2792. Min Act: -0.1700
Data Index: 6965813 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.2479. Min Act: -0.1700
Data Index: 2757038 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.2479. Min Act: -0.1700
Data Index: 5861781 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.2479. Min Act: -0.1700
Data Index: 8102471 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.2167. Min Act: -0.1700
Data Index: 6534837 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.1542. Min Act: -0.1699
Data Index: 8353929 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.1542. Min Act: -0.1700
Data Index: 6735056 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.1542. Min Act: -0.1700
Data Index: 1584209 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.1542. Min Act: -0.1700
Data Index: 1564451 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.1229. Min Act: -0.1700
Data Index: 2628771 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.0917. Min Act: -0.1700
Data Index: 8577156 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.0917. Min Act: -0.1700
Data Index: 538758 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.0604. Min Act: -0.1700
Data Index: 4116137 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3104. Min Range: -6.3104
Max Act: 6.0292. Min Act: -0.1700
Data Index: 7962653 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3104. Min Range: -6.3104
Max Act: 5.9979. Min Act: -0.1700
Data Index: 1984212 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3104. Min Range: -6.3104
Max Act: 5.9979. Min Act: -0.1700
Data Index: 5268650 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3104. Min Range: -6.3104
Max Act: 5.9667. Min Act: -0.1700
Data Index: 7017300 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3104. Min Range: -6.3104
Max Act: 5.9667. Min Act: -0.1700
Data Index: 7083166 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3104. Min Range: -6.3104
Max Act: 5.9667. Min Act: -0.1700
Data Index: 6637362 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19