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

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

Neuron 3514 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: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0003

Data Index: 327650 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0367. Min Act: -0.0003

Data Index: 450442 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0377. Min Act: -0.0002

Data Index: 785608 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0361. Min Act: -0.0002

Data Index: 367549 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0366. Min Act: -0.0003

Data Index: 855056 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0355. Min Act: -0.0002

Data Index: 399069 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1131551 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0333. Min Act: -0.0003

Data Index: 18486 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0329. Min Act: -0.0003

Data Index: 808208 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0307. Min Act: -0.0003

Data Index: 297682 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0289. Min Act: -0.0003

Data Index: 390162 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0282. Min Act: -0.0003

Data Index: 459481 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0309. Min Act: -0.0002

Data Index: 823442 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0305. Min Act: -0.0002

Data Index: 144903 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0295. Min Act: -0.0003

Data Index: 539243 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0305. Min Act: -0.0003

Data Index: 396649 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0289. Min Act: -0.0003

Data Index: 657707 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1071231 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1149174 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0299. Min Act: -0.0002

Data Index: 723302 (C4 (Web Text))

Max Activating Token Index: 121