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

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

Neuron 754 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: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0006

Data Index: 843419 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0451. Min Act: -0.0006

Data Index: 262240 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0397. Min Act: -0.0006

Data Index: 958508 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0344. Min Act: -0.0006

Data Index: 22591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1206866 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0327. Min Act: -0.0006

Data Index: 509450 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0369. Min Act: -0.0006

Data Index: 559137 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0324. Min Act: -0.0006

Data Index: 271624 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0413. Min Act: -0.0006

Data Index: 214433 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0326. Min Act: -0.0006

Data Index: 508504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1256872 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0321. Min Act: -0.0006

Data Index: 995602 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0299. Min Act: -0.0006

Data Index: 332884 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0312. Min Act: -0.0006

Data Index: 210175 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1233254 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1306548 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1311097 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1316797 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0325. Min Act: -0.0006

Data Index: 570276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0311. Min Act: -0.0006

Data Index: 899277 (C4 (Web Text))

Max Activating Token Index: 416