Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1197 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.4470. Min Act: -0.1700
Data Index: 3757000 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.3220. Min Act: -0.1700
Data Index: 8369992 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.2908. Min Act: -0.1699
Data Index: 2214592 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.2283. Min Act: -0.1700
Data Index: 5593489 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.2283. Min Act: -0.1700
Data Index: 5371255 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1970. Min Act: -0.1699
Data Index: 8356339 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1345. Min Act: -0.1700
Data Index: 1521997 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1033. Min Act: -0.1700
Data Index: 3784461 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1345. Min Act: -0.1700
Data Index: 6977217 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1033. Min Act: -0.1700
Data Index: 1615996 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1033. Min Act: -0.1700
Data Index: 5931041 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1033. Min Act: -0.1700
Data Index: 7733508 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.0720. Min Act: -0.1700
Data Index: 5331676 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.1345. Min Act: -0.1700
Data Index: 7691064 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.0720. Min Act: -0.1698
Data Index: 5999949 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.0408. Min Act: -0.1700
Data Index: 3988182 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.0720. Min Act: -0.1700
Data Index: 1491701 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.0720. Min Act: -0.1698
Data Index: 8144694 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.0720. Min Act: -0.1699
Data Index: 4818326 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4470. Min Range: -6.4470
Max Act: 6.0408. Min Act: -0.1700
Data Index: 7298254 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19