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

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

Neuron 4233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1045281 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1503. Min Act: -0.0000

Data Index: 291456 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1231295 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1441. Min Act: -0.0000

Data Index: 148442 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1526. Min Act: -0.0000

Data Index: 924687 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1401. Min Act: -0.0000

Data Index: 958954 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1046116 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1471. Min Act: -0.0000

Data Index: 925941 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1412881 (Python Code)

Max Activating Token Index: 721

Text #9

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1415. Min Act: -0.0000

Data Index: 436222 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1397. Min Act: -0.0000

Data Index: 456362 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1272. Min Act: -0.0000

Data Index: 135121 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1315. Min Act: -0.0000

Data Index: 144492 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1325. Min Act: -0.0000

Data Index: 767599 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1470281 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1306. Min Act: -0.0000

Data Index: 475625 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1484201 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1293. Min Act: -0.0000

Data Index: 434873 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1230. Min Act: -0.0000

Data Index: 268100 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1126362 (C4 (Web Text))

Max Activating Token Index: 623