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

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

Neuron 2372 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: 1.0340. Min Range: -1.0340

Max Act: 1.0340. Min Act: -0.0000

Data Index: 116208 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 1.0340. Min Range: -1.0340

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1079194 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.9039. Min Act: -0.0000

Data Index: 598321 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1656915 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8603. Min Act: -0.0000

Data Index: 789536 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7199. Min Act: -0.0000

Data Index: 360665 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8079. Min Act: -0.0000

Data Index: 131550 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1099895 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7271. Min Act: -0.0000

Data Index: 443500 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6981. Min Act: -0.0000

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6954. Min Act: -0.0000

Data Index: 822365 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7213. Min Act: -0.0000

Data Index: 627060 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6927. Min Act: -0.0000

Data Index: 352708 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1514480 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6701. Min Act: -0.0000

Data Index: 766990 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1495507 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7295. Min Act: -0.0000

Data Index: 512782 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1050042 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7474. Min Act: -0.0000

Data Index: 230802 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7112. Min Act: -0.0000

Data Index: 637200 (C4 (Web Text))

Max Activating Token Index: 663