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

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

Neuron 3478 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5868. Min Act: -0.0002

Data Index: 648658 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5657. Min Act: -0.0002

Data Index: 95005 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5677. Min Act: -0.0002

Data Index: 38895 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5366. Min Act: -0.0002

Data Index: 687235 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5220. Min Act: -0.0002

Data Index: 964817 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5329. Min Act: -0.0002

Data Index: 48843 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5271. Min Act: -0.0002

Data Index: 820437 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4834. Min Act: -0.0002

Data Index: 504902 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5020. Min Act: -0.0002

Data Index: 411356 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4377. Min Act: -0.0002

Data Index: 1358417 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4296. Min Act: -0.0002

Data Index: 1335006 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4204. Min Act: -0.0002

Data Index: 342605 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4585. Min Act: -0.0002

Data Index: 349217 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4149. Min Act: -0.0002

Data Index: 904995 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4199. Min Act: -0.0002

Data Index: 891698 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4238. Min Act: -0.0002

Data Index: 485716 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3889. Min Act: -0.0002

Data Index: 1278007 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3880. Min Act: -0.0002

Data Index: 575127 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3773. Min Act: -0.0002

Data Index: 1251460 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3839. Min Act: -0.0002

Data Index: 903228 (C4 (Web Text))

Max Activating Token Index: 640