Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4495 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.5664. Min Act: -0.1700
Data Index: 5168404 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.5664. Min Act: -0.1700
Data Index: 261790 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.5977. Min Act: -0.1700
Data Index: 4771740 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.5039. Min Act: -0.1700
Data Index: 3006340 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.5039. Min Act: -0.1700
Data Index: 3807350 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.5039. Min Act: -0.1700
Data Index: 4334384 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4727. Min Act: -0.1700
Data Index: 5207597 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 4027256 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 8817333 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 6553056 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4727. Min Act: -0.1700
Data Index: 3246461 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 6434557 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 8174302 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 3100163 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4102. Min Act: -0.1700
Data Index: 8698733 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4102. Min Act: -0.1700
Data Index: 6167842 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4102. Min Act: -0.1700
Data Index: 3544799 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 7151907 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.3789. Min Act: -0.1700
Data Index: 5441650 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5977. Min Range: -4.5977
Max Act: 4.4102. Min Act: -0.1700
Data Index: 3778757 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19