Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4078 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.3099. Min Act: -0.0001
Data Index: 705690 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.7462. Min Act: -0.0001
Data Index: 479929 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.2329. Min Act: -0.0001
Data Index: 1042683 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.0665. Min Act: -0.0001
Data Index: 49136 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.2040. Min Act: -0.0001
Data Index: 431230 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.2777. Min Act: -0.0001
Data Index: 718978 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.1649. Min Act: -0.0001
Data Index: 1000040 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.0378. Min Act: -0.0001
Data Index: 31733 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.9657. Min Act: -0.0001
Data Index: 879628 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.3600. Min Act: -0.0001
Data Index: 748580 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.7028. Min Act: -0.0001
Data Index: 496160 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.9698. Min Act: -0.0001
Data Index: 472311 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.0291. Min Act: -0.0001
Data Index: 559450 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.2886. Min Act: -0.0001
Data Index: 340048 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7462. Min Range: -2.7462
Max Act: 2.1145. Min Act: -0.0001
Data Index: 930564 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.7194. Min Act: -0.0001
Data Index: 972824 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.8454. Min Act: -0.0001
Data Index: 209679 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.9751. Min Act: -0.0001
Data Index: 866657 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.9507. Min Act: -0.0001
Data Index: 1262982 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7462. Min Range: -2.7462
Max Act: 1.9013. Min Act: -0.0001
Data Index: 1184731 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19