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

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

Neuron 19 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: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1627292 (Python Code)

Max Activating Token Index: 526

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1474136 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1467603 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1426047 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1518127 (Python Code)

Max Activating Token Index: 265

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0207. Min Act: -0.0002

Data Index: 613186 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1385030 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1381515 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0002

Data Index: 658415 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1381336 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0195. Min Act: -0.0002

Data Index: 351198 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1634755 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1599308 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1604830 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1459376 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1235919 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1633639 (Python Code)

Max Activating Token Index: 972

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1383455 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1319181 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1602579 (Python Code)

Max Activating Token Index: 443