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

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

Neuron 2050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.3550. Min Act: -0.0000

Data Index: 340596 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.4223. Min Act: -0.0000

Data Index: 645511 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.2142. Min Act: -0.0000

Data Index: 384707 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.1726. Min Act: -0.0000

Data Index: 1225585 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.0331. Min Act: -0.0000

Data Index: 60446 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.0850. Min Act: -0.0000

Data Index: 1180860 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.1954. Min Act: -0.0000

Data Index: 879610 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.0396. Min Act: -0.0000

Data Index: 1054584 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.0412. Min Act: -0.0000

Data Index: 202897 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.0313. Min Act: -0.0000

Data Index: 875274 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 2.4223. Min Range: -2.4223

Max Act: 2.0990. Min Act: -0.0000

Data Index: 450533 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.9883. Min Act: -0.0000

Data Index: 1002037 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.9670. Min Act: -0.0000

Data Index: 674757 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.9392. Min Act: -0.0000

Data Index: 138508 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.9010. Min Act: -0.0000

Data Index: 36739 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.8809. Min Act: -0.0000

Data Index: 992581 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.7918. Min Act: -0.0000

Data Index: 125772 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.7711. Min Act: -0.0000

Data Index: 174861 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.8382. Min Act: -0.0000

Data Index: 353438 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 2.4223. Min Range: -2.4223

Max Act: 1.8150. Min Act: -0.0000

Data Index: 50330 (C4 (Web Text))

Max Activating Token Index: 654