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

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

Neuron 3706 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.1486. Min Act: -0.0002

Data Index: 1044316 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.1583. Min Act: -0.0002

Data Index: 1336468 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.1630. Min Act: -0.0002

Data Index: 518759 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0168. Min Act: -0.0002

Data Index: 668820 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.2328. Min Act: -0.0002

Data Index: 755217 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0708. Min Act: -0.0002

Data Index: 242085 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0680. Min Act: -0.0002

Data Index: 988128 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0065. Min Act: -0.0002

Data Index: 1032857 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.1476. Min Act: -0.0002

Data Index: 1263252 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0430. Min Act: -0.0002

Data Index: 792416 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.1027. Min Act: -0.0002

Data Index: 974155 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0658. Min Act: -0.0002

Data Index: 1203867 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0335. Min Act: -0.0002

Data Index: 431061 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0424. Min Act: -0.0002

Data Index: 68174 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0587. Min Act: -0.0002

Data Index: 1228811 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9553. Min Act: -0.0002

Data Index: 851475 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0148. Min Act: -0.0002

Data Index: 789260 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9920. Min Act: -0.0002

Data Index: 584774 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8759. Min Act: -0.0001

Data Index: 575622 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9202. Min Act: -0.0002

Data Index: 675616 (C4 (Web Text))

Max Activating Token Index: 235