Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0000

Data Index: 177227 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0276. Min Act: -0.0000

Data Index: 756396 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0266. Min Act: -0.0001

Data Index: 770940 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1318707 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1015318 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1252718 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0251. Min Act: -0.0000

Data Index: 803773 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0261. Min Act: -0.0000

Data Index: 114670 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0247. Min Act: -0.0000

Data Index: 938567 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0237. Min Act: -0.0000

Data Index: 757223 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0227. Min Act: -0.0000

Data Index: 881169 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0262. Min Act: -0.0000

Data Index: 234762 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0245. Min Act: -0.0000

Data Index: 903568 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0243. Min Act: 0.0000

Data Index: 95160 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1518133 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0241. Min Act: -0.0000

Data Index: 323112 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1129064 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1285274 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1393395 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0241. Min Act: -0.0000

Data Index: 655254 (C4 (Web Text))

Max Activating Token Index: 990