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

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

Neuron 5733 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.4104. Min Act: -0.0000

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1412135 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1558148 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1306602 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1590792 (Python Code)

Max Activating Token Index: 958

Text #5

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1457453 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1496255 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1518136 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1338. Min Act: 0.0000

Data Index: 1596993 (Python Code)

Max Activating Token Index: 232

Text #9

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1611351 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1415. Min Act: 0.0000

Data Index: 1541097 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1499809 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1552169 (Python Code)

Max Activating Token Index: 201

Text #13

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1150. Min Act: -0.0000

Data Index: 1515751 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1482880 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1356810 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1503431 (Python Code)

Max Activating Token Index: 1002

Text #17

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1274. Min Act: -0.0000

Data Index: 1575326 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1400518 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0228. Min Act: -0.0000

Data Index: 176926 (C4 (Web Text))

Max Activating Token Index: 21