Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1176 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1283566 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9674. Min Act: -0.0000

Data Index: 355539 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7375. Min Act: -0.0000

Data Index: 822873 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7193. Min Act: -0.0000

Data Index: 627575 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7221. Min Act: -0.0000

Data Index: 640656 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7267. Min Act: -0.0000

Data Index: 70606 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7266. Min Act: -0.0000

Data Index: 437385 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7330. Min Act: -0.0000

Data Index: 856809 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1035277 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7035. Min Act: -0.0000

Data Index: 666133 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1619045 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6926. Min Act: -0.0000

Data Index: 961381 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6329. Min Act: -0.0000

Data Index: 548037 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6492. Min Act: -0.0000

Data Index: 237995 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1543184 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6590. Min Act: -0.0000

Data Index: 993361 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1647239 (Python Code)

Max Activating Token Index: 839

Text #17

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6380. Min Act: -0.0000

Data Index: 675110 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1384523 (Python Code)

Max Activating Token Index: 471

Text #19

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.6993. Min Act: -0.0000

Data Index: 408795 (C4 (Web Text))

Max Activating Token Index: 69