Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0189. Min Range: -5.0189
Max Act: 5.0189. Min Act: -0.1700
Data Index: 897382 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.8626. Min Act: -0.1700
Data Index: 8288348 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.8314. Min Act: -0.1700
Data Index: 4072597 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.8001. Min Act: -0.1700
Data Index: 5914528 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.8001. Min Act: -0.1700
Data Index: 623628 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7376. Min Act: -0.1700
Data Index: 2666055 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7376. Min Act: -0.1700
Data Index: 2172097 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7689. Min Act: -0.1700
Data Index: 7035393 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7376. Min Act: -0.1700
Data Index: 4479709 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7689. Min Act: -0.1700
Data Index: 776635 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7376. Min Act: -0.1700
Data Index: 1302805 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7376. Min Act: -0.1700
Data Index: 4464937 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7376. Min Act: -0.1700
Data Index: 4179609 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7064. Min Act: -0.1700
Data Index: 2968918 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7689. Min Act: -0.1700
Data Index: 5497958 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7376. Min Act: -0.1700
Data Index: 5828982 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7064. Min Act: -0.1700
Data Index: 8612833 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.7064. Min Act: -0.1700
Data Index: 787218 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.6751. Min Act: -0.1700
Data Index: 6999474 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0189. Min Range: -5.0189
Max Act: 4.6126. Min Act: -0.1700
Data Index: 6211059 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19