Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5666. Min Act: -0.1700
Data Index: 6411849 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5041. Min Act: -0.1700
Data Index: 1690514 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5041. Min Act: -0.1700
Data Index: 5523819 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5041. Min Act: -0.1700
Data Index: 3380162 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4729. Min Act: -0.1700
Data Index: 1726515 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5041. Min Act: -0.1700
Data Index: 215191 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5041. Min Act: -0.1700
Data Index: 3164051 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5041. Min Act: -0.1700
Data Index: 2086684 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5354. Min Act: -0.1700
Data Index: 7709742 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.5041. Min Act: -0.1700
Data Index: 7218815 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4729. Min Act: -0.1700
Data Index: 2775570 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4104. Min Act: -0.1700
Data Index: 5077744 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4416. Min Act: -0.1700
Data Index: 7009404 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4104. Min Act: -0.1700
Data Index: 4276059 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4104. Min Act: -0.1700
Data Index: 4329810 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4104. Min Act: -0.1700
Data Index: 2002410 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4416. Min Act: -0.1700
Data Index: 7411609 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4104. Min Act: -0.1700
Data Index: 4071446 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4104. Min Act: -0.1700
Data Index: 8637008 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5666. Min Range: -4.5666
Max Act: 4.4416. Min Act: -0.1700
Data Index: 6514735 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19