Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.9537. Min Act: -0.1700
Data Index: 6106356 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.9224. Min Act: -0.1700
Data Index: 5187655 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.8599. Min Act: -0.1700
Data Index: 626104 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.7974. Min Act: -0.1700
Data Index: 4435641 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.7974. Min Act: -0.1700
Data Index: 979123 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.7662. Min Act: -0.1700
Data Index: 5429407 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.6724. Min Act: -0.1700
Data Index: 2612628 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.6099. Min Act: -0.1700
Data Index: 4919167 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.5787. Min Act: -0.1700
Data Index: 7054254 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.6099. Min Act: -0.1700
Data Index: 5411628 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.5474. Min Act: -0.1700
Data Index: 1940168 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.5162. Min Act: -0.1700
Data Index: 7839849 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.4849. Min Act: -0.1700
Data Index: 497590 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.4849. Min Act: -0.1700
Data Index: 2531384 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.5162. Min Act: -0.1700
Data Index: 1291424 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.4849. Min Act: -0.1700
Data Index: 6227524 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.4537. Min Act: -0.1700
Data Index: 1402015 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.4224. Min Act: -0.1700
Data Index: 5199405 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.4224. Min Act: -0.1700
Data Index: 429373 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9537. Min Range: -6.9537
Max Act: 6.4224. Min Act: -0.1700
Data Index: 1562254 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19