Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2880 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1446. Min Act: -0.0000

Data Index: 487537 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1627294 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1521858 (Python Code)

Max Activating Token Index: 318

Text #3

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1000653 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1431103 (Python Code)

Max Activating Token Index: 883

Text #5

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1472440 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1389335 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1467403 (Python Code)

Max Activating Token Index: 468

Text #8

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1576936 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1365988 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1407960 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1576983 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1407660 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1105. Min Act: -0.0000

Data Index: 454262 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1540068 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1640116 (Python Code)

Max Activating Token Index: 202

Text #16

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1112. Min Act: -0.0000

Data Index: 383745 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1157. Min Act: -0.0000

Data Index: 790767 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1620341 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1502281 (Python Code)

Max Activating Token Index: 252