Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.8678. Min Act: -0.1700
Data Index: 3856538 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7740. Min Act: -0.1700
Data Index: 6124837 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7740. Min Act: -0.1700
Data Index: 1416103 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7428. Min Act: -0.1700
Data Index: 2455507 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7428. Min Act: -0.1699
Data Index: 6864054 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.6178. Min Act: -0.1700
Data Index: 4291604 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7428. Min Act: -0.1700
Data Index: 5369400 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7115. Min Act: -0.1699
Data Index: 3790539 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.6490. Min Act: -0.1700
Data Index: 8158279 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7115. Min Act: -0.1700
Data Index: 3173606 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.5553. Min Act: -0.1698
Data Index: 3060706 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.7115. Min Act: -0.1700
Data Index: 3741694 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.6490. Min Act: -0.1700
Data Index: 6209096 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.6178. Min Act: -0.1700
Data Index: 313428 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.4928. Min Act: -0.1700
Data Index: 2657765 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.5865. Min Act: -0.1700
Data Index: 2494775 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.5865. Min Act: -0.1700
Data Index: 4604092 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.5240. Min Act: -0.1698
Data Index: 7668915 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.6490. Min Act: -0.1700
Data Index: 2737967 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8678. Min Range: -5.8678
Max Act: 5.6490. Min Act: -0.1700
Data Index: 7786239 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19