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

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

Neuron 2509 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0361. Min Act: -0.0003

Data Index: 647871 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0416. Min Act: -0.0004

Data Index: 370716 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1222678 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0446. Min Act: -0.0003

Data Index: 418822 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0420. Min Act: -0.0003

Data Index: 21906 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0411. Min Act: -0.0003

Data Index: 810928 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1144372 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0429. Min Act: -0.0003

Data Index: 180647 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0418. Min Act: -0.0003

Data Index: 427732 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0372. Min Act: -0.0003

Data Index: 126084 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0438. Min Act: -0.0003

Data Index: 204315 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0413. Min Act: -0.0003

Data Index: 209799 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1095924 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0378. Min Act: -0.0004

Data Index: 800418 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1325445 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0391. Min Act: -0.0003

Data Index: 483644 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0405. Min Act: -0.0003

Data Index: 420770 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0374. Min Act: -0.0003

Data Index: 35143 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0388. Min Act: -0.0004

Data Index: 1331038 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0385. Min Act: -0.0003

Data Index: 266574 (C4 (Web Text))

Max Activating Token Index: 751