Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6130 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1792. Min Range: -7.1792
Max Act: 7.1792. Min Act: -0.1700
Data Index: 6758785 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1792. Min Range: -7.1792
Max Act: 7.1792. Min Act: -0.1700
Data Index: 6803463 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1792. Min Range: -7.1792
Max Act: 7.0230. Min Act: -0.1700
Data Index: 1964076 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.8980. Min Act: -0.1700
Data Index: 5081384 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.8355. Min Act: -0.1700
Data Index: 7705388 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.8355. Min Act: -0.1700
Data Index: 1921897 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.8355. Min Act: -0.1700
Data Index: 312668 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.8355. Min Act: -0.1700
Data Index: 3288001 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.8042. Min Act: -0.1700
Data Index: 5626914 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.7730. Min Act: -0.1700
Data Index: 2126028 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.7730. Min Act: -0.1700
Data Index: 8291905 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.7730. Min Act: -0.1700
Data Index: 2080070 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.7730. Min Act: -0.1700
Data Index: 5798513 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.7730. Min Act: -0.1700
Data Index: 3395821 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.7417. Min Act: -0.1700
Data Index: 3008416 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.7105. Min Act: -0.1700
Data Index: 8233437 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.6792. Min Act: -0.1700
Data Index: 4212130 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.6792. Min Act: -0.1700
Data Index: 2537122 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.6480. Min Act: -0.1700
Data Index: 1202226 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1792. Min Range: -7.1792
Max Act: 6.6480. Min Act: -0.1700
Data Index: 6161378 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19