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

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

Neuron 4531 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: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0000

Data Index: 496023 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0307. Min Act: -0.0000

Data Index: 443902 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1112834 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1096604 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1137113 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0319. Min Act: -0.0000

Data Index: 977982 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1279834 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1374438 (Python Code)

Max Activating Token Index: 564

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0277. Min Act: -0.0000

Data Index: 751719 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1249306 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0274. Min Act: -0.0000

Data Index: 746970 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0261. Min Act: -0.0000

Data Index: 1062883 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1337874 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0297. Min Act: -0.0000

Data Index: 843496 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0267. Min Act: -0.0000

Data Index: 834892 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0277. Min Act: -0.0000

Data Index: 213814 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0276. Min Act: -0.0000

Data Index: 130647 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0286. Min Act: -0.0000

Data Index: 589216 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0270. Min Act: -0.0001

Data Index: 312025 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0281. Min Act: -0.0000

Data Index: 380146 (C4 (Web Text))

Max Activating Token Index: 404