Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5316 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1308. Min Range: -5.1308
Max Act: 5.1308. Min Act: -0.1700
Data Index: 7730143 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.9433. Min Act: -0.1700
Data Index: 8020223 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.8808. Min Act: -0.1700
Data Index: 5984215 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.8808. Min Act: -0.1700
Data Index: 4091496 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.8496. Min Act: -0.1700
Data Index: 5984214 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.8496. Min Act: -0.1700
Data Index: 7589011 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.8183. Min Act: -0.1700
Data Index: 628136 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.7558. Min Act: -0.1700
Data Index: 362650 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.7871. Min Act: -0.1700
Data Index: 7730144 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.6933. Min Act: -0.1700
Data Index: 2603916 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.6308. Min Act: -0.1700
Data Index: 2787272 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5996. Min Act: -0.1700
Data Index: 3931503 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5683. Min Act: -0.1700
Data Index: 5117748 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5683. Min Act: -0.1700
Data Index: 3046206 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5683. Min Act: -0.1700
Data Index: 83488 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5683. Min Act: -0.1700
Data Index: 216949 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5683. Min Act: -0.1700
Data Index: 6627343 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5058. Min Act: -0.1700
Data Index: 6110734 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5058. Min Act: -0.1700
Data Index: 3525210 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1308. Min Range: -5.1308
Max Act: 4.5058. Min Act: -0.1700
Data Index: 2804096 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19