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

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

Neuron 3723 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2586. Min Act: -0.0002

Data Index: 826956 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2545. Min Act: -0.0003

Data Index: 106181 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2635. Min Act: -0.0003

Data Index: 627036 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2535. Min Act: -0.0003

Data Index: 221067 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2589. Min Act: -0.0002

Data Index: 368434 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2484. Min Act: -0.0003

Data Index: 761329 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2474. Min Act: -0.0003

Data Index: 828909 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2452. Min Act: -0.0002

Data Index: 1655262 (Python Code)

Max Activating Token Index: 583

Text #8

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2537. Min Act: -0.0003

Data Index: 1275862 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2601. Min Act: -0.0003

Data Index: 365367 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2410. Min Act: -0.0003

Data Index: 1245624 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2492. Min Act: -0.0002

Data Index: 1380063 (Python Code)

Max Activating Token Index: 516

Text #12

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2391. Min Act: -0.0003

Data Index: 359713 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2388. Min Act: -0.0003

Data Index: 1139310 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2365. Min Act: -0.0002

Data Index: 1061158 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2430. Min Act: -0.0003

Data Index: 289027 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2415. Min Act: -0.0002

Data Index: 725942 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2405. Min Act: -0.0003

Data Index: 776870 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2354. Min Act: -0.0002

Data Index: 366759 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.2635. Min Range: -0.2635

Max Act: 0.2260. Min Act: -0.0003

Data Index: 1061632 (C4 (Web Text))

Max Activating Token Index: 363