Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2553 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4227. Min Range: -11.4227
Max Act: 11.4227. Min Act: -0.1700
Data Index: 7654578 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4227. Min Range: -11.4227
Max Act: 11.1727. Min Act: -0.1700
Data Index: 8129771 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4227. Min Range: -11.4227
Max Act: 11.1727. Min Act: -0.1700
Data Index: 2709631 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4227. Min Range: -11.4227
Max Act: 11.1727. Min Act: -0.1700
Data Index: 897558 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4227. Min Range: -11.4227
Max Act: 11.0477. Min Act: -0.1700
Data Index: 4857170 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.9852. Min Act: -0.1700
Data Index: 5294040 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.8602. Min Act: -0.1700
Data Index: 2591866 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.9227. Min Act: -0.1700
Data Index: 5294039 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.9227. Min Act: -0.1700
Data Index: 2669548 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.9227. Min Act: -0.1700
Data Index: 5584199 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7977. Min Act: -0.1700
Data Index: 3940271 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7977. Min Act: -0.1700
Data Index: 6384460 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7977. Min Act: -0.1700
Data Index: 5118604 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7977. Min Act: -0.1700
Data Index: 8653932 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7352. Min Act: -0.1700
Data Index: 8283127 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7977. Min Act: -0.1700
Data Index: 4872506 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7352. Min Act: -0.1700
Data Index: 6682713 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.7352. Min Act: -0.1700
Data Index: 3104291 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.6727. Min Act: -0.1700
Data Index: 6930737 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4227. Min Range: -11.4227
Max Act: 10.6727. Min Act: -0.1700
Data Index: 8357564 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19