Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0909. Min Range: -5.0909
Max Act: 5.0909. Min Act: -0.1700
Data Index: 7024982 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0909. Min Range: -5.0909
Max Act: 5.0909. Min Act: -0.1700
Data Index: 7884492 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0909. Min Range: -5.0909
Max Act: 5.0597. Min Act: -0.1700
Data Index: 3529812 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9972. Min Act: -0.1700
Data Index: 8806119 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0909. Min Range: -5.0909
Max Act: 5.0284. Min Act: -0.1700
Data Index: 8628140 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9972. Min Act: -0.1700
Data Index: 2780176 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9659. Min Act: -0.1700
Data Index: 4810861 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9659. Min Act: -0.1700
Data Index: 5306066 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9347. Min Act: -0.1700
Data Index: 2714429 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9347. Min Act: -0.1700
Data Index: 2193311 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9659. Min Act: -0.1700
Data Index: 8326389 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9347. Min Act: -0.1700
Data Index: 8095269 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9034. Min Act: -0.1700
Data Index: 476150 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9659. Min Act: -0.1700
Data Index: 5666831 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9034. Min Act: -0.1700
Data Index: 1871190 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9034. Min Act: -0.1700
Data Index: 8085413 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9347. Min Act: -0.1700
Data Index: 410278 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9034. Min Act: -0.1700
Data Index: 3929079 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.9034. Min Act: -0.1700
Data Index: 2314452 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0909. Min Range: -5.0909
Max Act: 4.8722. Min Act: -0.1700
Data Index: 29663 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19