Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1205679 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.2436. Min Act: -0.0000

Data Index: 734762 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1187882 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1249849 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1324745 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.1145. Min Act: -0.0000

Data Index: 628047 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.1117. Min Act: -0.0000

Data Index: 350029 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1628566 (Python Code)

Max Activating Token Index: 744

Text #8

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.1540. Min Act: -0.0000

Data Index: 835191 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1233111 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.0858. Min Act: -0.0000

Data Index: 991902 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1235859 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.2731. Min Range: -1.2731

Max Act: 1.0187. Min Act: -0.0000

Data Index: 845481 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.2731. Min Range: -1.2731

Max Act: 0.9570. Min Act: -0.0000

Data Index: 658161 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.2731. Min Range: -1.2731

Max Act: 0.9316. Min Act: -0.0000

Data Index: 645875 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 1.2731. Min Range: -1.2731

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1083182 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.2731. Min Range: -1.2731

Max Act: 0.9179. Min Act: -0.0000

Data Index: 494046 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 1.2731. Min Range: -1.2731

Max Act: 0.9173. Min Act: -0.0000

Data Index: 961908 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.2731. Min Range: -1.2731

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1626503 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 1.2731. Min Range: -1.2731

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1337598 (C4 (Web Text))

Max Activating Token Index: 892