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

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

Neuron 3465 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1238. Min Range: -1.1238

Max Act: 1.0241. Min Act: -0.0001

Data Index: 833854 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.1238. Min Range: -1.1238

Max Act: 1.1238. Min Act: -0.0001

Data Index: 843051 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9256. Min Act: -0.0001

Data Index: 866581 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9200. Min Act: -0.0001

Data Index: 72909 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7855. Min Act: -0.0001

Data Index: 1292023 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7440. Min Act: -0.0001

Data Index: 1194362 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7301. Min Act: -0.0001

Data Index: 1251217 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9039. Min Act: -0.0001

Data Index: 809726 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6810. Min Act: -0.0001

Data Index: 191883 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6327. Min Act: -0.0001

Data Index: 1145199 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1343940 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6681. Min Act: -0.0001

Data Index: 1076001 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6600. Min Act: -0.0001

Data Index: 294518 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7300. Min Act: -0.0001

Data Index: 282884 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6165. Min Act: -0.0001

Data Index: 926129 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6778. Min Act: -0.0001

Data Index: 250968 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6295. Min Act: -0.0001

Data Index: 1271258 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7189. Min Act: -0.0001

Data Index: 871101 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.6056. Min Act: -0.0001

Data Index: 917539 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.5856. Min Act: -0.0001

Data Index: 1356312 (C4 (Web Text))

Max Activating Token Index: 371