Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1525 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1491. Min Act: -0.0003

Data Index: 74994 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1344. Min Act: -0.0003

Data Index: 845682 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1323. Min Act: -0.0002

Data Index: 757987 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1335. Min Act: -0.0003

Data Index: 30320 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1327. Min Act: -0.0003

Data Index: 913471 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1324. Min Act: -0.0004

Data Index: 872575 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1289. Min Act: -0.0003

Data Index: 1240998 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1272. Min Act: -0.0003

Data Index: 266184 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1293. Min Act: -0.0002

Data Index: 403722 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1233. Min Act: -0.0004

Data Index: 681107 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1219. Min Act: -0.0003

Data Index: 1090471 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1270. Min Act: -0.0003

Data Index: 1206901 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1097356 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1208. Min Act: -0.0003

Data Index: 406055 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1255. Min Act: -0.0003

Data Index: 1035758 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1207. Min Act: -0.0003

Data Index: 1216464 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1186. Min Act: -0.0003

Data Index: 1232755 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1214556 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1173. Min Act: -0.0002

Data Index: 1255833 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1219. Min Act: -0.0003

Data Index: 506738 (C4 (Web Text))

Max Activating Token Index: 430