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

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

Neuron 925 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.9191. Min Act: -0.0002

Data Index: 1170237 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.9194. Min Act: -0.0002

Data Index: 851048 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.9288. Min Act: -0.0002

Data Index: 1259260 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.8245. Min Act: -0.0002

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.7393. Min Act: -0.0002

Data Index: 1292000 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.6583. Min Act: -0.0002

Data Index: 104284 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.7994. Min Act: -0.0002

Data Index: 271451 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.8898. Min Act: -0.0002

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.7131. Min Act: -0.0002

Data Index: 1301225 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.7138. Min Act: -0.0002

Data Index: 1301056 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.6577. Min Act: -0.0002

Data Index: 38438 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.6863. Min Act: -0.0002

Data Index: 378072 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.8646. Min Act: -0.0002

Data Index: 1323880 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.7421. Min Act: -0.0002

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.6189. Min Act: -0.0002

Data Index: 333881 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.6700. Min Act: -0.0002

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.6953. Min Act: -0.0002

Data Index: 258364 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.7181. Min Act: -0.0002

Data Index: 1184785 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.5020. Min Act: -0.0002

Data Index: 700016 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.7349. Min Act: -0.0002

Data Index: 1195141 (C4 (Web Text))

Max Activating Token Index: 391