Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 513 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1242938 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0223. Min Act: -0.0006

Data Index: 848155 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0218. Min Act: -0.0006

Data Index: 888687 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0218. Min Act: -0.0006

Data Index: 99951 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1165926 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0209. Min Act: -0.0006

Data Index: 17618 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0209. Min Act: -0.0006

Data Index: 480809 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0209. Min Act: -0.0006

Data Index: 427788 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1046397 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0206. Min Act: -0.0006

Data Index: 936995 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0194. Min Act: -0.0006

Data Index: 571264 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0200. Min Act: -0.0006

Data Index: 589973 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1088448 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1246203 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0193. Min Act: -0.0006

Data Index: 63019 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0196. Min Act: -0.0006

Data Index: 67342 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0197. Min Act: -0.0006

Data Index: 349659 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0193. Min Act: -0.0005

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0197. Min Act: -0.0006

Data Index: 384800 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0190. Min Act: -0.0006

Data Index: 748606 (C4 (Web Text))

Max Activating Token Index: 932