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

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

Neuron 2412 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1327. Min Act: -0.0003

Data Index: 897345 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1358. Min Act: -0.0003

Data Index: 1301483 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1207. Min Act: -0.0003

Data Index: 270298 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1283. Min Act: -0.0003

Data Index: 535469 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1279. Min Act: -0.0003

Data Index: 1089232 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1153. Min Act: -0.0003

Data Index: 646202 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1026260 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1147. Min Act: -0.0003

Data Index: 1177213 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1173. Min Act: -0.0003

Data Index: 956208 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1045. Min Act: -0.0003

Data Index: 697009 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1109. Min Act: -0.0003

Data Index: 486381 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1148. Min Act: -0.0003

Data Index: 676167 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1107. Min Act: -0.0003

Data Index: 299162 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1057. Min Act: -0.0003

Data Index: 764187 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1102. Min Act: -0.0003

Data Index: 737809 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1031786 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1085. Min Act: -0.0003

Data Index: 1209599 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1029. Min Act: -0.0003

Data Index: 321255 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1119. Min Act: -0.0003

Data Index: 599614 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1064. Min Act: -0.0003

Data Index: 540759 (C4 (Web Text))

Max Activating Token Index: 864