Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6149 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 8750220 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0781. Min Act: -0.1700
Data Index: 8720618 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 6672205 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 6317699 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9843. Min Act: -0.1700
Data Index: 5637921 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9843. Min Act: -0.1700
Data Index: 8720616 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9843. Min Act: -0.1700
Data Index: 831268 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 7023241 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 5742219 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6450799 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 5208113 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6265924 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 2793125 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6032207 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 2169837 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 8334995 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1546458 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1163426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9218. Min Act: -0.1700
Data Index: 404866 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9218. Min Act: -0.1700
Data Index: 5982691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19