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

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

Neuron 233 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: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0006

Data Index: 557820 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0385. Min Act: -0.0006

Data Index: 101020 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1339591 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0327. Min Act: -0.0006

Data Index: 123883 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1246178 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0295. Min Act: -0.0006

Data Index: 115717 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0293. Min Act: -0.0006

Data Index: 833454 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0274. Min Act: -0.0006

Data Index: 606241 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0278. Min Act: -0.0006

Data Index: 746946 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0253. Min Act: -0.0006

Data Index: 422014 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0265. Min Act: -0.0006

Data Index: 301328 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0266. Min Act: -0.0006

Data Index: 222063 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1030824 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0260. Min Act: -0.0006

Data Index: 215819 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0264. Min Act: -0.0006

Data Index: 895646 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0263. Min Act: -0.0006

Data Index: 985944 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0256. Min Act: -0.0006

Data Index: 739970 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1027009 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0255. Min Act: -0.0006

Data Index: 66616 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0248. Min Act: -0.0006

Data Index: 76783 (C4 (Web Text))

Max Activating Token Index: 171