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

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

Neuron 2893 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0328. Min Act: -0.0003

Data Index: 794251 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1283538 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0317. Min Act: -0.0003

Data Index: 657865 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0003

Data Index: 739009 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1492489 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0243. Min Act: -0.0003

Data Index: 308928 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1538254 (Python Code)

Max Activating Token Index: 895

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1121238 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1330112 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0278. Min Act: -0.0003

Data Index: 334373 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0267. Min Act: -0.0003

Data Index: 87964 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1594321 (Python Code)

Max Activating Token Index: 305

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0282. Min Act: -0.0003

Data Index: 431999 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0277. Min Act: -0.0004

Data Index: 150331 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0269. Min Act: -0.0003

Data Index: 110031 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1505722 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1534640 (Python Code)

Max Activating Token Index: 540

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1478971 (Python Code)

Max Activating Token Index: 828

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1386128 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1361522 (Python Code)

Max Activating Token Index: 767