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

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

Neuron 1985 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.2031. Min Act: 0.0000

Data Index: 352844 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.2528. Min Act: 0.0000

Data Index: 1306278 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.2233. Min Act: 0.0000

Data Index: 774543 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.0978. Min Act: -0.0000

Data Index: 941430 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.0474. Min Act: 0.0000

Data Index: 991502 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.9647. Min Act: 0.0000

Data Index: 1064063 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8697. Min Act: 0.0000

Data Index: 1165293 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8140. Min Act: -0.0000

Data Index: 388623 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8540. Min Act: 0.0000

Data Index: 805477 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8297. Min Act: -0.0000

Data Index: 578357 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8518. Min Act: -0.0000

Data Index: 448268 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7979. Min Act: 0.0000

Data Index: 696461 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8070. Min Act: -0.0000

Data Index: 31068 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8044. Min Act: -0.0000

Data Index: 309345 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.8065. Min Act: -0.0000

Data Index: 148876 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7869. Min Act: 0.0000

Data Index: 290840 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7503. Min Act: -0.0000

Data Index: 909323 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7545. Min Act: 0.0000

Data Index: 1252700 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7783. Min Act: -0.0000

Data Index: 671153 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7742. Min Act: -0.0000

Data Index: 443386 (C4 (Web Text))

Max Activating Token Index: 751