Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5830 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.8934. Min Act: -0.0001

Data Index: 45768 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.8051. Min Act: -0.0001

Data Index: 80072 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.7389. Min Act: -0.0001

Data Index: 767628 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1326532 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.7282. Min Act: -0.0001

Data Index: 121667 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1092901 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.7103. Min Act: -0.0001

Data Index: 1012949 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6452. Min Act: -0.0001

Data Index: 205171 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6781. Min Act: -0.0001

Data Index: 427250 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6522. Min Act: -0.0001

Data Index: 548016 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6860. Min Act: -0.0001

Data Index: 161387 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6200. Min Act: -0.0001

Data Index: 477411 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.5827. Min Act: -0.0001

Data Index: 576082 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6334. Min Act: -0.0001

Data Index: 69350 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6161. Min Act: -0.0001

Data Index: 1240096 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6340. Min Act: -0.0001

Data Index: 96767 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6493. Min Act: -0.0001

Data Index: 617927 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6681. Min Act: -0.0001

Data Index: 602760 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6408. Min Act: -0.0001

Data Index: 377483 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.8934. Min Range: -0.8934

Max Act: 0.6375. Min Act: -0.0001

Data Index: 432739 (C4 (Web Text))

Max Activating Token Index: 137