Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 947 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2691. Min Act: -0.0002

Data Index: 1070266 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2677. Min Act: -0.0002

Data Index: 547627 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2363. Min Act: -0.0002

Data Index: 84156 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2440. Min Act: -0.0001

Data Index: 448841 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2218. Min Act: -0.0001

Data Index: 569937 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2457. Min Act: -0.0002

Data Index: 1058595 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2448. Min Act: -0.0002

Data Index: 119269 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1038073 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2377. Min Act: -0.0002

Data Index: 1358912 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2315. Min Act: -0.0002

Data Index: 560538 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2237. Min Act: -0.0001

Data Index: 732231 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2214. Min Act: -0.0002

Data Index: 364116 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2122. Min Act: -0.0002

Data Index: 220478 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2200. Min Act: -0.0001

Data Index: 283883 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2181. Min Act: -0.0002

Data Index: 669322 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2144. Min Act: -0.0002

Data Index: 389384 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2149. Min Act: -0.0001

Data Index: 844426 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2126. Min Act: -0.0002

Data Index: 226440 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2211. Min Act: -0.0001

Data Index: 363946 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1239486 (C4 (Web Text))

Max Activating Token Index: 894