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

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

Neuron 4300 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1314514 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.4049. Min Act: -0.0000

Data Index: 783209 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.4014. Min Act: -0.0000

Data Index: 959505 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.3775. Min Act: -0.0000

Data Index: 1055967 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.3654. Min Act: -0.0000

Data Index: 938888 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1533684 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.3197. Min Act: -0.0000

Data Index: 765030 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.3060. Min Act: -0.0000

Data Index: 92450 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.2171. Min Act: -0.0000

Data Index: 290944 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1720. Min Act: -0.0000

Data Index: 208919 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.2112. Min Act: -0.0000

Data Index: 804051 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1332. Min Act: -0.0000

Data Index: 1357566 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0622. Min Act: -0.0000

Data Index: 318719 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1238. Min Act: -0.0000

Data Index: 161457 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1194. Min Act: -0.0000

Data Index: 240645 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1885. Min Act: -0.0000

Data Index: 407337 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1086. Min Act: -0.0000

Data Index: 75714 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0763. Min Act: -0.0000

Data Index: 531818 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1284791 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1237590 (C4 (Web Text))

Max Activating Token Index: 356