Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.5390. Min Act: -0.1700
Data Index: 485220 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.4765. Min Act: -0.1700
Data Index: 7978720 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.4453. Min Act: -0.1700
Data Index: 1157999 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.4140. Min Act: -0.1700
Data Index: 7730162 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.4140. Min Act: -0.1700
Data Index: 8196662 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3828. Min Act: -0.1700
Data Index: 6158860 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3828. Min Act: -0.1700
Data Index: 5785259 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3828. Min Act: -0.1700
Data Index: 7770046 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 2864865 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 5483475 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 4960436 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 6326863 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 1533213 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3203. Min Act: -0.1700
Data Index: 8332578 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 3952007 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3515. Min Act: -0.1700
Data Index: 1102212 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3203. Min Act: -0.1700
Data Index: 1755010 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3203. Min Act: -0.1700
Data Index: 7075246 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3203. Min Act: -0.1700
Data Index: 1909196 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5390. Min Range: -5.5390
Max Act: 5.3203. Min Act: -0.1700
Data Index: 7261418 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19