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

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

Neuron 1448 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: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1223528 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1049975 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0492. Min Act: -0.0003

Data Index: 964637 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0440. Min Act: -0.0003

Data Index: 715817 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1159516 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0424. Min Act: -0.0003

Data Index: 505685 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0389. Min Act: -0.0003

Data Index: 158634 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0403. Min Act: -0.0003

Data Index: 553354 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0378. Min Act: -0.0003

Data Index: 194418 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0377. Min Act: -0.0003

Data Index: 367436 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0448. Min Act: -0.0003

Data Index: 850279 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1337963 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0411. Min Act: -0.0003

Data Index: 700812 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0426. Min Act: -0.0003

Data Index: 594953 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0425. Min Act: -0.0003

Data Index: 414792 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1031003 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0361. Min Act: -0.0003

Data Index: 516200 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0359. Min Act: -0.0003

Data Index: 729567 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0381. Min Act: -0.0003

Data Index: 118788 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0391. Min Act: -0.0004

Data Index: 770902 (C4 (Web Text))

Max Activating Token Index: 607