Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.2508. Min Act: -0.1700
Data Index: 6772138 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.2036. Min Act: -0.1700
Data Index: 4347061 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1407. Min Act: -0.1700
Data Index: 5365368 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1092. Min Act: -0.1700
Data Index: 5520944 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0776. Min Act: -0.1700
Data Index: 6109137 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0776. Min Act: -0.1700
Data Index: 7723054 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0619. Min Act: -0.1700
Data Index: 982421 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0619. Min Act: -0.1700
Data Index: 1319006 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0461. Min Act: -0.1700
Data Index: 7404021 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0461. Min Act: -0.1700
Data Index: 4966059 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0303. Min Act: -0.1700
Data Index: 6974790 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0303. Min Act: -0.1700
Data Index: 6536364 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0145. Min Act: -0.1700
Data Index: 7027805 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0145. Min Act: -0.1700
Data Index: 5647441 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2508. Min Range: -3.2508
Max Act: 2.9987. Min Act: -0.1700
Data Index: 4354910 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2508. Min Range: -3.2508
Max Act: 2.9829. Min Act: -0.1700
Data Index: 789546 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2508. Min Range: -3.2508
Max Act: 2.9987. Min Act: -0.1700
Data Index: 5133719 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2508. Min Range: -3.2508
Max Act: 2.9829. Min Act: -0.1700
Data Index: 4426542 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2508. Min Range: -3.2508
Max Act: 2.9829. Min Act: -0.1700
Data Index: 5441834 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2508. Min Range: -3.2508
Max Act: 2.9829. Min Act: -0.1700
Data Index: 305673 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19