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

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

Neuron 1595 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5289. Min Range: -2.5289

Max Act: 2.5289. Min Act: -0.0000

Data Index: 849601 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 2.5289. Min Range: -2.5289

Max Act: 2.4685. Min Act: -0.0000

Data Index: 1487460 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 2.5289. Min Range: -2.5289

Max Act: 2.3835. Min Act: -0.0000

Data Index: 1436191 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 2.5289. Min Range: -2.5289

Max Act: 2.2238. Min Act: -0.0000

Data Index: 1586234 (Python Code)

Max Activating Token Index: 29

Text #4

Max Range: 2.5289. Min Range: -2.5289

Max Act: 2.2237. Min Act: -0.0000

Data Index: 1486180 (Python Code)

Max Activating Token Index: 851

Text #5

Max Range: 2.5289. Min Range: -2.5289

Max Act: 2.1190. Min Act: -0.0000

Data Index: 1616499 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 2.5289. Min Range: -2.5289

Max Act: 2.0303. Min Act: -0.0000

Data Index: 1382312 (Python Code)

Max Activating Token Index: 817

Text #7

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1423379 (Python Code)

Max Activating Token Index: 601

Text #8

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.8994. Min Act: -0.0000

Data Index: 336741 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.7570. Min Act: -0.0000

Data Index: 764235 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1154258 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.9150. Min Act: -0.0000

Data Index: 657951 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.8190. Min Act: -0.0000

Data Index: 437049 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.7421. Min Act: -0.0000

Data Index: 14903 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.7629. Min Act: -0.0000

Data Index: 390772 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.6482. Min Act: -0.0000

Data Index: 1444162 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.6505. Min Act: -0.0000

Data Index: 791253 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.5228. Min Act: -0.0000

Data Index: 660218 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1065248 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 2.5289. Min Range: -2.5289

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1537867 (Python Code)

Max Activating Token Index: 366