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

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

Neuron 2289 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0001

Data Index: 751834 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8478. Min Act: -0.0001

Data Index: 833610 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7987. Min Act: -0.0001

Data Index: 212264 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8245. Min Act: -0.0001

Data Index: 607339 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8346. Min Act: -0.0001

Data Index: 131087 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6946. Min Act: -0.0001

Data Index: 1101661 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7167. Min Act: -0.0001

Data Index: 363959 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6948. Min Act: -0.0001

Data Index: 26676 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6758. Min Act: -0.0001

Data Index: 337206 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6923. Min Act: -0.0001

Data Index: 393759 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6882. Min Act: -0.0001

Data Index: 792381 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7286. Min Act: -0.0001

Data Index: 694081 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6127. Min Act: -0.0001

Data Index: 961746 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1321195 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6301. Min Act: -0.0001

Data Index: 90951 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6255. Min Act: -0.0001

Data Index: 275166 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1260438 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6210. Min Act: -0.0001

Data Index: 379389 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.5740. Min Act: -0.0001

Data Index: 118001 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6385. Min Act: -0.0001

Data Index: 727318 (C4 (Web Text))

Max Activating Token Index: 102