Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6327. Min Range: -8.6327
Max Act: 8.6327. Min Act: -0.1700
Data Index: 8304943 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6327. Min Range: -8.6327
Max Act: 8.6327. Min Act: -0.1700
Data Index: 728428 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6327. Min Range: -8.6327
Max Act: 8.4452. Min Act: -0.1700
Data Index: 2192262 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6327. Min Range: -8.6327
Max Act: 8.3827. Min Act: -0.1700
Data Index: 1921400 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6327. Min Range: -8.6327
Max Act: 8.3202. Min Act: -0.1700
Data Index: 884370 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6327. Min Range: -8.6327
Max Act: 8.2264. Min Act: -0.1700
Data Index: 8352388 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6327. Min Range: -8.6327
Max Act: 8.0389. Min Act: -0.1700
Data Index: 6890060 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.8827. Min Act: -0.1700
Data Index: 8806926 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.8202. Min Act: -0.1700
Data Index: 8110159 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.7264. Min Act: -0.1700
Data Index: 5565714 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.6639. Min Act: -0.1700
Data Index: 7372031 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.5702. Min Act: -0.1700
Data Index: 1085233 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.5702. Min Act: -0.1700
Data Index: 872723 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.5077. Min Act: -0.1700
Data Index: 4045623 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.3514. Min Act: -0.1700
Data Index: 3632009 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.2889. Min Act: -0.1700
Data Index: 5279760 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.2577. Min Act: -0.1700
Data Index: 2645572 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.2577. Min Act: -0.1700
Data Index: 2063691 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.2264. Min Act: -0.1700
Data Index: 4340403 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6327. Min Range: -8.6327
Max Act: 7.2577. Min Act: -0.1700
Data Index: 4963596 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19