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

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

Neuron 4039 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.2237. Min Act: -0.0000

Data Index: 902045 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1530. Min Act: -0.0000

Data Index: 101522 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1747. Min Act: -0.0000

Data Index: 265908 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0751. Min Act: -0.0000

Data Index: 839382 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9861. Min Act: -0.0000

Data Index: 301134 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1213496 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1333102 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0183. Min Act: -0.0000

Data Index: 711128 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1241110 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9302. Min Act: -0.0000

Data Index: 112312 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9963. Min Act: -0.0000

Data Index: 708270 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1467026 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1055205 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8428. Min Act: -0.0000

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8825. Min Act: -0.0000

Data Index: 534072 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1031804 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8652. Min Act: -0.0000

Data Index: 717557 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8429. Min Act: -0.0000

Data Index: 109761 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8773. Min Act: -0.0000

Data Index: 818372 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7674. Min Act: -0.0000

Data Index: 767727 (C4 (Web Text))

Max Activating Token Index: 898