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

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

Neuron 5093 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0003

Data Index: 863226 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1426 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0419. Min Act: -0.0003

Data Index: 781008 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0405. Min Act: -0.0003

Data Index: 737257 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1383531 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1233858 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0380. Min Act: -0.0003

Data Index: 429631 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0367. Min Act: -0.0003

Data Index: 120895 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0362. Min Act: -0.0002

Data Index: 699876 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0360. Min Act: -0.0003

Data Index: 169627 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0365. Min Act: -0.0003

Data Index: 621521 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0355. Min Act: -0.0003

Data Index: 168119 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1027186 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1641636 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0347. Min Act: -0.0003

Data Index: 872198 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1155856 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1643572 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0345. Min Act: -0.0003

Data Index: 401000 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0331. Min Act: -0.0002

Data Index: 981010 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0341. Min Act: -0.0002

Data Index: 70736 (C4 (Web Text))

Max Activating Token Index: 28