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

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

Neuron 321 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.3267. Min Act: -0.0002

Data Index: 473762 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.3129. Min Act: -0.0002

Data Index: 397597 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2997. Min Act: -0.0002

Data Index: 1357859 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2812. Min Act: -0.0002

Data Index: 1219235 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2776. Min Act: -0.0002

Data Index: 743247 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2693. Min Act: -0.0002

Data Index: 945534 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2546. Min Act: -0.0002

Data Index: 206577 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2487. Min Act: -0.0002

Data Index: 21868 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2277. Min Act: -0.0002

Data Index: 828554 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2423. Min Act: -0.0002

Data Index: 1115301 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2308. Min Act: -0.0002

Data Index: 639126 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2399. Min Act: -0.0002

Data Index: 1062148 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2390. Min Act: -0.0002

Data Index: 22819 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2293. Min Act: -0.0002

Data Index: 568023 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2255. Min Act: -0.0002

Data Index: 847459 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2227. Min Act: -0.0002

Data Index: 383726 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2278. Min Act: -0.0002

Data Index: 528534 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2126. Min Act: -0.0002

Data Index: 1015964 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2122. Min Act: -0.0002

Data Index: 550408 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.3267. Min Range: -0.3267

Max Act: 0.2187. Min Act: -0.0002

Data Index: 1337768 (C4 (Web Text))

Max Activating Token Index: 64