Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1709 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2539. Min Range: -5.2539
Max Act: 5.2539. Min Act: -0.1700
Data Index: 95382 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2539. Min Range: -5.2539
Max Act: 5.1289. Min Act: -0.1700
Data Index: 8007065 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2539. Min Range: -5.2539
Max Act: 5.0664. Min Act: -0.1700
Data Index: 7533173 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2539. Min Range: -5.2539
Max Act: 5.0664. Min Act: -0.1700
Data Index: 3001506 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2539. Min Range: -5.2539
Max Act: 5.0352. Min Act: -0.1700
Data Index: 2295189 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.9727. Min Act: -0.1700
Data Index: 718801 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.9727. Min Act: -0.1700
Data Index: 7214337 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.9727. Min Act: -0.1700
Data Index: 7712671 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8789. Min Act: -0.1700
Data Index: 2718239 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.9102. Min Act: -0.1700
Data Index: 6101973 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.9102. Min Act: -0.1700
Data Index: 3051105 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8477. Min Act: -0.1700
Data Index: 4439226 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8789. Min Act: -0.1700
Data Index: 839158 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8789. Min Act: -0.1700
Data Index: 208358 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8477. Min Act: -0.1700
Data Index: 6543253 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8477. Min Act: -0.1700
Data Index: 4595485 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8477. Min Act: -0.1700
Data Index: 4201227 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8164. Min Act: -0.1700
Data Index: 2938441 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.8164. Min Act: -0.1700
Data Index: 959009 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2539. Min Range: -5.2539
Max Act: 4.7852. Min Act: -0.1700
Data Index: 1879001 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19