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

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

Neuron 4301 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: 1.8983. Min Range: -1.8983

Max Act: 1.8983. Min Act: -0.0000

Data Index: 493956 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.8080. Min Act: -0.0000

Data Index: 601924 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.4608. Min Act: -0.0000

Data Index: 85305 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1046743 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.4226. Min Act: -0.0000

Data Index: 1000842 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.2257. Min Act: -0.0000

Data Index: 565883 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1083276 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.3563. Min Act: -0.0000

Data Index: 336095 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1316044 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.2529. Min Act: -0.0000

Data Index: 410476 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.1318. Min Act: -0.0000

Data Index: 66063 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.0623. Min Act: -0.0000

Data Index: 680169 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.0568. Min Act: -0.0000

Data Index: 197397 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.0498. Min Act: -0.0000

Data Index: 475224 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.0101. Min Act: -0.0000

Data Index: 943199 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.8983. Min Range: -1.8983

Max Act: 0.8790. Min Act: -0.0000

Data Index: 115689 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.0200. Min Act: -0.0000

Data Index: 295479 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.8983. Min Range: -1.8983

Max Act: 1.0560. Min Act: -0.0000

Data Index: 25468 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.8983. Min Range: -1.8983

Max Act: 0.9394. Min Act: -0.0000

Data Index: 576021 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.8983. Min Range: -1.8983

Max Act: 0.9756. Min Act: -0.0000

Data Index: 208355 (C4 (Web Text))

Max Activating Token Index: 277