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

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

Neuron 2698 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: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1573299 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1644840 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1525973 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1515486 (Python Code)

Max Activating Token Index: 427

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1630904 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1393909 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1543902 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1419416 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1450367 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1423661 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1631689 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1588143 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1525747 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1473151 (Python Code)

Max Activating Token Index: 120

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1406311 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1634569 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1637886 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1409381 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1440812 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1403358 (Python Code)

Max Activating Token Index: 130