Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1278 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0003

Data Index: 544127 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0333. Min Act: -0.0003

Data Index: 790484 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0324. Min Act: -0.0003

Data Index: 960335 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0320. Min Act: -0.0003

Data Index: 778725 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1535492 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1655744 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1032644 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1468409 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0215. Min Act: -0.0003

Data Index: 126646 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0250. Min Act: -0.0003

Data Index: 837331 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0207. Min Act: -0.0003

Data Index: 39970 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0217. Min Act: -0.0003

Data Index: 487958 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0222. Min Act: -0.0003

Data Index: 31120 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1654767 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0211. Min Act: -0.0003

Data Index: 731625 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1144577 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0201. Min Act: -0.0003

Data Index: 951844 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1596810 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1584470 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1060837 (C4 (Web Text))

Max Activating Token Index: 550