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

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

Neuron 2178 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: 0.3364. Min Range: -0.3364

Max Act: 0.3364. Min Act: -0.0000

Data Index: 650169 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2589. Min Act: -0.0000

Data Index: 919222 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2521. Min Act: -0.0000

Data Index: 301330 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2581. Min Act: -0.0000

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2417. Min Act: -0.0000

Data Index: 465670 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2318. Min Act: -0.0000

Data Index: 426231 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2184. Min Act: -0.0000

Data Index: 727973 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2233. Min Act: -0.0000

Data Index: 658810 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2216. Min Act: -0.0000

Data Index: 889802 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1138136 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2248. Min Act: -0.0000

Data Index: 507232 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2228. Min Act: -0.0000

Data Index: 182460 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2137. Min Act: -0.0000

Data Index: 816452 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2185. Min Act: -0.0000

Data Index: 144785 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2041. Min Act: -0.0000

Data Index: 30433 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2152. Min Act: -0.0000

Data Index: 67232 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1171290 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2203. Min Act: -0.0000

Data Index: 936285 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2017. Min Act: -0.0000

Data Index: 420289 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 357