Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.9780. Min Act: -0.1700
Data Index: 1757588 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4468. Min Act: -0.1700
Data Index: 6814336 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4468. Min Act: -0.1700
Data Index: 1238138 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4468. Min Act: -0.1700
Data Index: 3259760 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4468. Min Act: -0.1700
Data Index: 5119385 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4155. Min Act: -0.1700
Data Index: 1063821 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4155. Min Act: -0.1700
Data Index: 5518487 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4155. Min Act: -0.1700
Data Index: 5026677 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.4155. Min Act: -0.1700
Data Index: 4379052 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.3530. Min Act: -0.1700
Data Index: 7700386 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.3218. Min Act: -0.1700
Data Index: 1195948 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1968. Min Act: -0.1700
Data Index: 713507 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1968. Min Act: -0.1700
Data Index: 3249432 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 6130684 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1343. Min Act: -0.1700
Data Index: 8215662 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 1790706 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 7668041 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 7499471 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1343. Min Act: -0.1700
Data Index: 5505067 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9780. Min Range: -6.9780
Max Act: 6.1343. Min Act: -0.1700
Data Index: 2856358 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19