Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3429 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0948. Min Range: -4.0948

Max Act: 4.0948. Min Act: -0.0000

Data Index: 133784 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.2634. Min Act: -0.0000

Data Index: 1110903 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.8882. Min Act: -0.0000

Data Index: 1085249 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.6132. Min Act: 0.0000

Data Index: 433168 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.2828. Min Act: -0.0000

Data Index: 224309 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.1253. Min Act: -0.0000

Data Index: 801085 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.2555. Min Act: -0.0000

Data Index: 767869 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.5131. Min Act: -0.0000

Data Index: 284068 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.9079. Min Act: 0.0000

Data Index: 263040 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.0091. Min Act: -0.0000

Data Index: 513814 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.0142. Min Act: -0.0000

Data Index: 367470 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.7070. Min Act: -0.0000

Data Index: 234469 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.8071. Min Act: -0.0000

Data Index: 737566 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.5362. Min Act: 0.0000

Data Index: 691795 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 4.0948. Min Range: -4.0948

Max Act: 3.0196. Min Act: 0.0000

Data Index: 281175 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.7133. Min Act: -0.0000

Data Index: 812168 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.3473. Min Act: -0.0000

Data Index: 684280 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.3381. Min Act: -0.0000

Data Index: 741888 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.3650. Min Act: -0.0000

Data Index: 1003044 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 4.0948. Min Range: -4.0948

Max Act: 2.5358. Min Act: -0.0000

Data Index: 1219225 (C4 (Web Text))

Max Activating Token Index: 475