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

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

Neuron 1544 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: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1144801 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0003

Data Index: 725998 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1089685 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1067230 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1074830 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0273. Min Act: -0.0003

Data Index: 255734 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0271. Min Act: -0.0003

Data Index: 25570 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0275. Min Act: -0.0003

Data Index: 152576 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0271. Min Act: -0.0003

Data Index: 566202 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0269. Min Act: -0.0003

Data Index: 80406 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0269. Min Act: -0.0004

Data Index: 770879 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1652701 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0266. Min Act: -0.0003

Data Index: 333749 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0261. Min Act: -0.0003

Data Index: 25539 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0262. Min Act: -0.0004

Data Index: 858369 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0261. Min Act: -0.0003

Data Index: 100183 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1103252 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1423261 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0259. Min Act: -0.0003

Data Index: 518942 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0254. Min Act: -0.0004

Data Index: 984291 (C4 (Web Text))

Max Activating Token Index: 492