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

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

Neuron 4898 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.6802. Min Act: -0.0000

Data Index: 307966 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5537. Min Act: -0.0000

Data Index: 725318 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5637. Min Act: -0.0000

Data Index: 569246 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1053730 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1243751 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5273. Min Act: -0.0000

Data Index: 600091 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5335. Min Act: -0.0000

Data Index: 135762 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5322. Min Act: -0.0000

Data Index: 513131 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5199. Min Act: -0.0000

Data Index: 351186 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1053030 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4912. Min Act: -0.0000

Data Index: 874242 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4675. Min Act: -0.0000

Data Index: 552672 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1270406 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1226890 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4608. Min Act: -0.0000

Data Index: 24096 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4686. Min Act: -0.0000

Data Index: 221321 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4277. Min Act: -0.0000

Data Index: 854562 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4257. Min Act: -0.0000

Data Index: 559572 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4355. Min Act: 0.0000

Data Index: 620435 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4319. Min Act: -0.0000

Data Index: 508233 (C4 (Web Text))

Max Activating Token Index: 420