Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 664 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1458. Min Act: -0.0002

Data Index: 978348 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1419. Min Act: -0.0002

Data Index: 1103789 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1216. Min Act: -0.0002

Data Index: 283919 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1183. Min Act: -0.0002

Data Index: 662789 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1173. Min Act: -0.0002

Data Index: 914243 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1179. Min Act: -0.0002

Data Index: 656892 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1191. Min Act: -0.0003

Data Index: 1194675 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1170. Min Act: -0.0002

Data Index: 70726 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1164. Min Act: -0.0002

Data Index: 732732 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1150. Min Act: -0.0002

Data Index: 506231 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1145. Min Act: -0.0002

Data Index: 880849 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1116. Min Act: -0.0002

Data Index: 782629 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1112. Min Act: -0.0002

Data Index: 825436 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1354193 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1128. Min Act: -0.0002

Data Index: 295840 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1091. Min Act: -0.0002

Data Index: 979704 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1092. Min Act: -0.0002

Data Index: 601686 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1081. Min Act: -0.0002

Data Index: 966583 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1077. Min Act: -0.0002

Data Index: 846324 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1049. Min Act: -0.0002

Data Index: 601249 (C4 (Web Text))

Max Activating Token Index: 825