Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 91 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0005

Data Index: 207241 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1295. Min Act: -0.0005

Data Index: 483126 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1268. Min Act: -0.0005

Data Index: 1306935 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1237. Min Act: -0.0005

Data Index: 927102 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1190. Min Act: -0.0005

Data Index: 104436 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1133. Min Act: -0.0005

Data Index: 576981 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1079. Min Act: -0.0005

Data Index: 334730 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1165. Min Act: -0.0005

Data Index: 1279110 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1163. Min Act: -0.0005

Data Index: 199649 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1135. Min Act: -0.0005

Data Index: 312804 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1095. Min Act: -0.0005

Data Index: 1310645 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1135. Min Act: -0.0005

Data Index: 681371 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1116. Min Act: -0.0005

Data Index: 1058286 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1109. Min Act: -0.0005

Data Index: 1189762 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1145. Min Act: -0.0005

Data Index: 2582 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1021. Min Act: -0.0005

Data Index: 607162 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1050. Min Act: -0.0005

Data Index: 819910 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1085. Min Act: -0.0005

Data Index: 192587 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1015. Min Act: -0.0005

Data Index: 1193502 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1014. Min Act: -0.0005

Data Index: 881617 (C4 (Web Text))

Max Activating Token Index: 719