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

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

Neuron 547 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: 2.3504. Min Range: -2.3504

Max Act: 2.3504. Min Act: 0.0000

Data Index: 317516 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 2.3504. Min Range: -2.3504

Max Act: 2.2268. Min Act: -0.0000

Data Index: 1062421 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.9386. Min Act: -0.0000

Data Index: 1052925 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 2.3504. Min Range: -2.3504

Max Act: 2.0328. Min Act: -0.0000

Data Index: 517618 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.9038. Min Act: -0.0000

Data Index: 848939 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.8923. Min Act: -0.0000

Data Index: 1270497 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.8928. Min Act: -0.0000

Data Index: 153038 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.8371. Min Act: 0.0001

Data Index: 302204 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.7426. Min Act: -0.0000

Data Index: 550936 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.7349. Min Act: -0.0000

Data Index: 15572 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.6324. Min Act: -0.0000

Data Index: 371316 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.7549. Min Act: -0.0000

Data Index: 2073 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.8105. Min Act: 0.0000

Data Index: 931338 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.7181. Min Act: -0.0000

Data Index: 378597 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.7692. Min Act: -0.0000

Data Index: 80632 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.5780. Min Act: -0.0000

Data Index: 950344 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.5823. Min Act: -0.0000

Data Index: 950932 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.6161. Min Act: 0.0000

Data Index: 975648 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.6537. Min Act: 0.0000

Data Index: 623021 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 2.3504. Min Range: -2.3504

Max Act: 1.5430. Min Act: 0.0000

Data Index: 114269 (C4 (Web Text))

Max Activating Token Index: 75