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

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

Neuron 5039 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1242051 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2835. Min Act: -0.0000

Data Index: 284075 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.3594. Min Act: -0.0000

Data Index: 479629 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1159226 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1391168 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0367. Min Act: -0.0000

Data Index: 924358 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1337040 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0125. Min Act: -0.0000

Data Index: 971930 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1210200 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1614571 (Python Code)

Max Activating Token Index: 811

Text #10

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9831. Min Act: -0.0000

Data Index: 392204 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0203. Min Act: -0.0000

Data Index: 264363 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9891. Min Act: -0.0000

Data Index: 214694 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1296186 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0459. Min Act: -0.0000

Data Index: 91080 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9275. Min Act: -0.0000

Data Index: 858643 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0330. Min Act: -0.0000

Data Index: 850711 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9592. Min Act: -0.0000

Data Index: 192529 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0221. Min Act: -0.0000

Data Index: 304835 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0223. Min Act: -0.0000

Data Index: 11592 (C4 (Web Text))

Max Activating Token Index: 426