Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5496 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.8314. Min Act: -0.1700
Data Index: 3266558 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.6439. Min Act: -0.1700
Data Index: 3266557 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.5501. Min Act: -0.1700
Data Index: 8763135 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.4876. Min Act: -0.1700
Data Index: 316480 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.3939. Min Act: -0.1700
Data Index: 3266556 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.3314. Min Act: -0.1700
Data Index: 853253 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.2689. Min Act: -0.1700
Data Index: 4602389 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.2376. Min Act: -0.1700
Data Index: 2567389 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.2689. Min Act: -0.1700
Data Index: 2849784 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.1126. Min Act: -0.1700
Data Index: 692538 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.1126. Min Act: -0.1700
Data Index: 316481 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.0814. Min Act: -0.1700
Data Index: 2342511 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.0501. Min Act: -0.1700
Data Index: 5177471 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.0501. Min Act: -0.1700
Data Index: 1925853 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.0501. Min Act: -0.1700
Data Index: 3844357 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8314. Min Range: -7.8314
Max Act: 7.0189. Min Act: -0.1700
Data Index: 8827581 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8314. Min Range: -7.8314
Max Act: 6.9876. Min Act: -0.1700
Data Index: 4891806 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8314. Min Range: -7.8314
Max Act: 6.9876. Min Act: -0.1700
Data Index: 4456190 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8314. Min Range: -7.8314
Max Act: 6.9251. Min Act: -0.1700
Data Index: 8451476 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8314. Min Range: -7.8314
Max Act: 6.9251. Min Act: -0.1700
Data Index: 264861 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19