Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2686 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0001

Data Index: 461412 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1710. Min Act: -0.0001

Data Index: 603617 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1226951 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1024158 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1249. Min Act: -0.0001

Data Index: 316501 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1296. Min Act: -0.0001

Data Index: 397511 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1242. Min Act: -0.0001

Data Index: 673185 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1186. Min Act: -0.0001

Data Index: 721693 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1178. Min Act: -0.0001

Data Index: 691403 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1219. Min Act: -0.0001

Data Index: 198100 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1205. Min Act: -0.0001

Data Index: 590230 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1234. Min Act: -0.0001

Data Index: 491738 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1069884 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1138. Min Act: -0.0001

Data Index: 879551 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1220151 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1141. Min Act: -0.0001

Data Index: 980438 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1185960 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1126. Min Act: -0.0001

Data Index: 212453 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1246481 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1273344 (C4 (Web Text))

Max Activating Token Index: 812