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

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

Neuron 4571 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6215. Min Act: -0.0000

Data Index: 19661 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5723. Min Act: -0.0000

Data Index: 731144 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5354. Min Act: -0.0000

Data Index: 852207 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5467. Min Act: -0.0000

Data Index: 84746 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5264. Min Act: -0.0000

Data Index: 558002 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1064014 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1230844 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4434. Min Act: -0.0000

Data Index: 743836 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1321014 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4811. Min Act: -0.0000

Data Index: 236259 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4779. Min Act: -0.0000

Data Index: 119922 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1358528 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4411. Min Act: -0.0000

Data Index: 101948 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1305653 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4745. Min Act: -0.0000

Data Index: 585827 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4537. Min Act: -0.0000

Data Index: 127215 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1240800 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1263844 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4564. Min Act: -0.0000

Data Index: 927223 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1079538 (C4 (Web Text))

Max Activating Token Index: 407