Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2764 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.9247. Min Act: -0.0000

Data Index: 647202 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1280742 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.8094. Min Act: -0.0000

Data Index: 511138 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.8312. Min Act: -0.0000

Data Index: 870788 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.8238. Min Act: -0.0000

Data Index: 241356 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7746. Min Act: -0.0001

Data Index: 857687 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7307. Min Act: -0.0000

Data Index: 491127 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7065. Min Act: -0.0000

Data Index: 950829 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1323903 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7426. Min Act: -0.0000

Data Index: 462211 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6782. Min Act: -0.0000

Data Index: 12692 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7163. Min Act: -0.0000

Data Index: 882387 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6597. Min Act: -0.0000

Data Index: 138168 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1018204 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6939. Min Act: -0.0001

Data Index: 336119 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6745. Min Act: -0.0000

Data Index: 632244 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6995. Min Act: -0.0000

Data Index: 468236 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6681. Min Act: -0.0000

Data Index: 426773 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7169. Min Act: -0.0000

Data Index: 520038 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6441. Min Act: -0.0000

Data Index: 169977 (C4 (Web Text))

Max Activating Token Index: 643