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

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

Neuron 910 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0002

Data Index: 327640 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1101998 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1253. Min Act: -0.0002

Data Index: 607300 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1192. Min Act: -0.0002

Data Index: 934170 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1230. Min Act: -0.0002

Data Index: 1000197 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1254933 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1193818 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1168. Min Act: -0.0002

Data Index: 543378 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1168. Min Act: -0.0002

Data Index: 296663 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1157. Min Act: -0.0002

Data Index: 860033 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1145. Min Act: -0.0002

Data Index: 32723 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1332918 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1145. Min Act: -0.0002

Data Index: 264496 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1039899 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1224889 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1134. Min Act: -0.0002

Data Index: 400011 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1056. Min Act: -0.0002

Data Index: 212778 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1103. Min Act: -0.0002

Data Index: 584918 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1112. Min Act: -0.0002

Data Index: 362950 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1171008 (C4 (Web Text))

Max Activating Token Index: 782