Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1917. Min Range: -9.1917
Max Act: 9.1917. Min Act: -0.1700
Data Index: 6148605 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.9417. Min Act: -0.1700
Data Index: 8587332 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.7542. Min Act: -0.1700
Data Index: 519344 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.6292. Min Act: -0.1700
Data Index: 4385538 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5667. Min Act: -0.1700
Data Index: 6189072 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5667. Min Act: -0.1700
Data Index: 3053077 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5667. Min Act: -0.1700
Data Index: 8650055 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 6805560 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5667. Min Act: -0.1700
Data Index: 1207211 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 2600133 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 359086 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 1677954 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 4524362 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 6410592 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 5973838 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 4555888 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 6668567 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 3019177 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 663450 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.3792. Min Act: -0.1700
Data Index: 96330 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19