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

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

Neuron 470 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: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0005

Data Index: 1299333 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1279. Min Act: -0.0005

Data Index: 982845 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1178. Min Act: -0.0005

Data Index: 1358369 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1172. Min Act: -0.0005

Data Index: 1171230 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1183. Min Act: -0.0005

Data Index: 898314 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1147. Min Act: -0.0005

Data Index: 1325416 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1097. Min Act: -0.0005

Data Index: 976957 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1115. Min Act: -0.0005

Data Index: 911498 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1143. Min Act: -0.0005

Data Index: 805963 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1046. Min Act: -0.0005

Data Index: 463209 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1134. Min Act: -0.0005

Data Index: 598439 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1072. Min Act: -0.0005

Data Index: 1265117 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1108. Min Act: -0.0005

Data Index: 994541 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1083. Min Act: -0.0005

Data Index: 1159816 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1083. Min Act: -0.0005

Data Index: 1207074 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1015. Min Act: -0.0005

Data Index: 324451 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1068. Min Act: -0.0005

Data Index: 551553 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1126. Min Act: -0.0005

Data Index: 503678 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1011. Min Act: -0.0005

Data Index: 1276862 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1118. Min Act: -0.0005

Data Index: 191 (C4 (Web Text))

Max Activating Token Index: 58