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

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

Neuron 3883 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: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1050699 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0755. Min Act: -0.0003

Data Index: 500387 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0493. Min Act: -0.0002

Data Index: 607080 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1130018 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1647183 (Python Code)

Max Activating Token Index: 132

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0426. Min Act: -0.0003

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0368. Min Act: -0.0003

Data Index: 402830 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1253464 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1564034 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0314. Min Act: -0.0003

Data Index: 534650 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0228. Min Act: -0.0003

Data Index: 534943 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1645867 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1371672 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1637083 (Python Code)

Max Activating Token Index: 288

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1380450 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0254. Min Act: -0.0002

Data Index: 250444 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1206509 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1272932 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1392300 (Python Code)

Max Activating Token Index: 935

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0287. Min Act: -0.0003

Data Index: 546567 (C4 (Web Text))

Max Activating Token Index: 87