Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.4729. Min Act: -0.1700
Data Index: 1429757 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.4104. Min Act: -0.1700
Data Index: 3812271 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.1291. Min Act: -0.1700
Data Index: 6585179 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.1291. Min Act: -0.1700
Data Index: 5847590 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0979. Min Act: -0.1700
Data Index: 7300982 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0666. Min Act: -0.1700
Data Index: 4881768 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0354. Min Act: -0.1700
Data Index: 8538479 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0666. Min Act: -0.1700
Data Index: 7365168 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0354. Min Act: -0.1700
Data Index: 1638875 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0041. Min Act: -0.1700
Data Index: 3141956 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0041. Min Act: -0.1700
Data Index: 3962320 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0041. Min Act: -0.1700
Data Index: 8451863 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4729. Min Range: -5.4729
Max Act: 5.0041. Min Act: -0.1700
Data Index: 4494144 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4729. Min Range: -5.4729
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2044041 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4729. Min Range: -5.4729
Max Act: 4.9729. Min Act: -0.1700
Data Index: 4193551 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4729. Min Range: -5.4729
Max Act: 4.9729. Min Act: -0.1700
Data Index: 3886902 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4729. Min Range: -5.4729
Max Act: 4.9416. Min Act: -0.1700
Data Index: 6013676 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4729. Min Range: -5.4729
Max Act: 4.9416. Min Act: -0.1700
Data Index: 2522629 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4729. Min Range: -5.4729
Max Act: 4.9416. Min Act: -0.1700
Data Index: 354850 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4729. Min Range: -5.4729
Max Act: 4.9416. Min Act: -0.1700
Data Index: 2388923 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19