Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 263 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1645511 (Python Code)

Max Activating Token Index: 399

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1483615 (Python Code)

Max Activating Token Index: 279

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0279. Min Act: -0.0003

Data Index: 884306 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1554284 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1574227 (Python Code)

Max Activating Token Index: 623

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1327018 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1447438 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1391826 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0249. Min Act: -0.0003

Data Index: 263761 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1123708 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0247. Min Act: -0.0003

Data Index: 721423 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0247. Min Act: -0.0003

Data Index: 115600 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0238. Min Act: -0.0003

Data Index: 52492 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1215539 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1413383 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1573646 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1507537 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0233. Min Act: -0.0003

Data Index: 683587 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0236. Min Act: -0.0003

Data Index: 586596 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1366169 (Python Code)

Max Activating Token Index: 110