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

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

Neuron 3459 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.5983. Min Act: -0.0001

Data Index: 1342818 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2743. Min Act: -0.0001

Data Index: 838534 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.1870. Min Act: -0.0000

Data Index: 571440 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2546. Min Act: -0.0001

Data Index: 603563 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.1748. Min Act: -0.0001

Data Index: 733057 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1076080 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9613. Min Act: -0.0001

Data Index: 1213228 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.0059. Min Act: -0.0000

Data Index: 293287 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9545. Min Act: -0.0001

Data Index: 904678 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.0369. Min Act: -0.0001

Data Index: 300133 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.0024. Min Act: -0.0001

Data Index: 574484 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9653. Min Act: -0.0001

Data Index: 563638 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.0127. Min Act: -0.0001

Data Index: 617881 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9444. Min Act: -0.0000

Data Index: 522612 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.8999. Min Act: -0.0000

Data Index: 943112 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.8952. Min Act: -0.0001

Data Index: 873012 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9283. Min Act: -0.0000

Data Index: 828147 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.8351. Min Act: -0.0001

Data Index: 537930 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9967. Min Act: -0.0001

Data Index: 634174 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9005. Min Act: -0.0001

Data Index: 182516 (C4 (Web Text))

Max Activating Token Index: 548