Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6119 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1523. Min Range: -7.1523
Max Act: 7.1523. Min Act: -0.1700
Data Index: 6213157 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1523. Min Range: -7.1523
Max Act: 7.0898. Min Act: -0.1700
Data Index: 7555780 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.7148. Min Act: -0.1700
Data Index: 642715 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.6836. Min Act: -0.1700
Data Index: 2680990 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.5273. Min Act: -0.1700
Data Index: 8584578 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.4961. Min Act: -0.1700
Data Index: 759527 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.4648. Min Act: -0.1700
Data Index: 5409959 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.4648. Min Act: -0.1700
Data Index: 8676470 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.4023. Min Act: -0.1700
Data Index: 671164 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3711. Min Act: -0.1700
Data Index: 6651427 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3711. Min Act: -0.1700
Data Index: 1294844 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.4023. Min Act: -0.1700
Data Index: 1682725 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3711. Min Act: -0.1700
Data Index: 3213802 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3398. Min Act: -0.1700
Data Index: 7242614 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3398. Min Act: -0.1700
Data Index: 635298 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 38892 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 2053674 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 7867128 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 2630750 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1523. Min Range: -7.1523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 7640035 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19