Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.6361. Min Act: -0.1700
Data Index: 4252990 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.6048. Min Act: -0.1700
Data Index: 8760873 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.4486. Min Act: -0.1700
Data Index: 3128739 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.3548. Min Act: -0.1700
Data Index: 2409889 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.3236. Min Act: -0.1700
Data Index: 8403543 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.3236. Min Act: -0.1700
Data Index: 3646207 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.2923. Min Act: -0.1700
Data Index: 4991655 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.2611. Min Act: -0.1700
Data Index: 274517 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6947404 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.2298. Min Act: -0.1700
Data Index: 3707249 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1585251 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1986. Min Act: -0.1700
Data Index: 3169502 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1361. Min Act: -0.1700
Data Index: 5982199 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1361. Min Act: -0.1700
Data Index: 7334187 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1361. Min Act: -0.1700
Data Index: 7075109 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1361. Min Act: -0.1700
Data Index: 4940452 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1361. Min Act: -0.1700
Data Index: 2898682 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1361. Min Act: -0.1700
Data Index: 3095647 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1048. Min Act: -0.1700
Data Index: 2338932 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6361. Min Range: -5.6361
Max Act: 5.1048. Min Act: -0.1700
Data Index: 2000996 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19