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

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

Neuron 4997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0469. Min Act: -0.0002

Data Index: 225204 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0002

Data Index: 989447 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0467. Min Act: -0.0002

Data Index: 624793 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0422. Min Act: -0.0002

Data Index: 156282 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0429. Min Act: -0.0002

Data Index: 843999 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0411. Min Act: -0.0002

Data Index: 137757 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1295601 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0456. Min Act: -0.0002

Data Index: 297549 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1136228 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0440. Min Act: -0.0002

Data Index: 965048 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1327412 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1297528 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0401. Min Act: -0.0002

Data Index: 101624 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0458. Min Act: -0.0002

Data Index: 598057 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0446. Min Act: -0.0002

Data Index: 106924 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1312998 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0419. Min Act: -0.0002

Data Index: 835528 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0400. Min Act: -0.0002

Data Index: 285576 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0401. Min Act: -0.0002

Data Index: 891852 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0456. Min Act: -0.0002

Data Index: 304737 (C4 (Web Text))

Max Activating Token Index: 281