Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1503 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1088072 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0357. Min Act: -0.0003

Data Index: 76849 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0332. Min Act: -0.0003

Data Index: 70881 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0333. Min Act: -0.0003

Data Index: 920101 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1598814 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0317. Min Act: -0.0003

Data Index: 618773 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1540911 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0300. Min Act: -0.0003

Data Index: 176756 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0307. Min Act: -0.0003

Data Index: 820959 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0306. Min Act: -0.0003

Data Index: 102672 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1229260 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1365406 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0301. Min Act: -0.0003

Data Index: 3971 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1287155 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1545943 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1307783 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1511511 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0310. Min Act: -0.0003

Data Index: 278428 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0305. Min Act: -0.0003

Data Index: 556172 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1007323 (C4 (Web Text))

Max Activating Token Index: 819