Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.0876. Min Range: -5.0876
Max Act: 5.0876. Min Act: -0.1700
Data Index: 7688572 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9626. Min Act: -0.1700
Data Index: 6563107 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9626. Min Act: -0.1700
Data Index: 1549002 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0876. Min Range: -5.0876
Max Act: 5.0251. Min Act: -0.1700
Data Index: 610238 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9314. Min Act: -0.1700
Data Index: 8378611 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9626. Min Act: -0.1700
Data Index: 606324 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9314. Min Act: -0.1700
Data Index: 3115332 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9314. Min Act: -0.1700
Data Index: 2115452 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9001. Min Act: -0.1700
Data Index: 2356787 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.9001. Min Act: -0.1700
Data Index: 3220467 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8376. Min Act: -0.1700
Data Index: 3623577 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8376. Min Act: -0.1700
Data Index: 737483 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8376. Min Act: -0.1700
Data Index: 433590 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8376. Min Act: -0.1700
Data Index: 3159976 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8376. Min Act: -0.1700
Data Index: 4505692 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8376. Min Act: -0.1700
Data Index: 722437 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8064. Min Act: -0.1700
Data Index: 2744430 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8064. Min Act: -0.1700
Data Index: 177371 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8064. Min Act: -0.1700
Data Index: 3846970 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0876. Min Range: -5.0876
Max Act: 4.8064. Min Act: -0.1700
Data Index: 3453360 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19