Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3279 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.8845. Min Act: -0.0001

Data Index: 598590 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.6725. Min Act: -0.0001

Data Index: 662407 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.7167. Min Act: -0.0001

Data Index: 1003124 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.5047. Min Act: -0.0001

Data Index: 1086305 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.5149. Min Act: -0.0001

Data Index: 1157791 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.4175. Min Act: -0.0001

Data Index: 307140 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.5070. Min Act: -0.0001

Data Index: 349572 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.4941. Min Act: -0.0001

Data Index: 451566 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.4251. Min Act: -0.0001

Data Index: 380321 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.4743. Min Act: -0.0001

Data Index: 971889 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.7015. Min Act: -0.0001

Data Index: 976182 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.3926. Min Act: -0.0001

Data Index: 1336452 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.3789. Min Act: -0.0001

Data Index: 180612 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.3600. Min Act: -0.0001

Data Index: 504341 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.4263. Min Act: -0.0001

Data Index: 174018 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.2515. Min Act: -0.0001

Data Index: 669850 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.2385. Min Act: -0.0001

Data Index: 1296350 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.4261. Min Act: -0.0001

Data Index: 744564 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.2223. Min Act: -0.0001

Data Index: 1251815 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.8845. Min Range: -1.8845

Max Act: 1.1179. Min Act: -0.0001

Data Index: 1116782 (C4 (Web Text))

Max Activating Token Index: 698