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

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

Neuron 4256 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0002

Data Index: 582262 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1035004 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1032084 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0327. Min Act: -0.0002

Data Index: 334409 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0314. Min Act: -0.0002

Data Index: 207890 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0310. Min Act: -0.0002

Data Index: 540156 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0311. Min Act: -0.0002

Data Index: 802452 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0297. Min Act: -0.0002

Data Index: 573912 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0303. Min Act: -0.0002

Data Index: 986511 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0300. Min Act: -0.0002

Data Index: 835674 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0301. Min Act: -0.0002

Data Index: 81440 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1210908 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0299. Min Act: -0.0002

Data Index: 407693 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0298. Min Act: -0.0002

Data Index: 711752 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0292. Min Act: -0.0002

Data Index: 261092 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0289. Min Act: -0.0002

Data Index: 70493 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0284. Min Act: -0.0002

Data Index: 126594 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0285. Min Act: -0.0002

Data Index: 475803 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0289. Min Act: -0.0002

Data Index: 183633 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1340051 (C4 (Web Text))

Max Activating Token Index: 361