Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5453 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.4255. Min Act: -0.1700
Data Index: 6902890 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.3005. Min Act: -0.1700
Data Index: 604807 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.2068. Min Act: -0.1700
Data Index: 7319333 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.2068. Min Act: -0.1700
Data Index: 4917572 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.1443. Min Act: -0.1700
Data Index: 1181439 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.0505. Min Act: -0.1700
Data Index: 6529278 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.0505. Min Act: -0.1700
Data Index: 5736086 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4255. Min Range: -6.4255
Max Act: 6.0193. Min Act: -0.1700
Data Index: 2843668 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7885772 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9880. Min Act: -0.1700
Data Index: 1392049 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7885773 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9880. Min Act: -0.1700
Data Index: 5714492 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9255. Min Act: -0.1700
Data Index: 2132148 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9568. Min Act: -0.1700
Data Index: 797659 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9568. Min Act: -0.1700
Data Index: 716740 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9568. Min Act: -0.1700
Data Index: 4737318 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9255. Min Act: -0.1700
Data Index: 4516817 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9255. Min Act: -0.1700
Data Index: 7885774 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.9255. Min Act: -0.1700
Data Index: 7885777 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4255. Min Range: -6.4255
Max Act: 5.8943. Min Act: -0.1700
Data Index: 7885776 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19