Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4165 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.2035. Min Act: -0.0002

Data Index: 666399 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.1632. Min Act: -0.0002

Data Index: 338694 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.2812. Min Act: -0.0002

Data Index: 494488 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.1776. Min Act: -0.0002

Data Index: 299283 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.0899. Min Act: -0.0002

Data Index: 632797 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.0151. Min Act: -0.0002

Data Index: 794751 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.0695. Min Act: -0.0002

Data Index: 995126 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.1000. Min Act: -0.0002

Data Index: 1219616 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.0535. Min Act: -0.0002

Data Index: 182338 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 4.2812. Min Range: -4.2812

Max Act: 4.0273. Min Act: -0.0002

Data Index: 130085 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.9445. Min Act: -0.0002

Data Index: 226345 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.9223. Min Act: -0.0002

Data Index: 76753 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.9226. Min Act: -0.0002

Data Index: 760707 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.9824. Min Act: -0.0002

Data Index: 1026534 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.8290. Min Act: -0.0002

Data Index: 1267451 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.8216. Min Act: -0.0002

Data Index: 992653 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.8122. Min Act: -0.0002

Data Index: 1330793 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.8270. Min Act: -0.0002

Data Index: 644532 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.8015. Min Act: -0.0002

Data Index: 1201053 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 4.2812. Min Range: -4.2812

Max Act: 3.8677. Min Act: -0.0002

Data Index: 212400 (C4 (Web Text))

Max Activating Token Index: 823