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

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

Neuron 2100 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1728. Min Act: -0.0001

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1027728 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1164148 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1230562 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1247. Min Act: -0.0001

Data Index: 514574 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1238324 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1183. Min Act: -0.0001

Data Index: 448081 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1131. Min Act: -0.0001

Data Index: 872270 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1300. Min Act: -0.0001

Data Index: 364863 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1212476 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1207. Min Act: -0.0001

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1209487 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1111. Min Act: -0.0001

Data Index: 327472 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1113. Min Act: -0.0001

Data Index: 89303 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1120. Min Act: -0.0001

Data Index: 993984 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1126. Min Act: -0.0001

Data Index: 964023 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1129. Min Act: -0.0001

Data Index: 830750 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1193. Min Act: -0.0001

Data Index: 973526 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1067. Min Act: -0.0001

Data Index: 581484 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1082. Min Act: -0.0001

Data Index: 988201 (C4 (Web Text))

Max Activating Token Index: 523