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

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

Neuron 2998 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: 0.1767. Min Range: -0.1767

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1547134 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1294. Min Act: -0.0002

Data Index: 326414 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1137. Min Act: -0.0002

Data Index: 360548 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1500259 (Python Code)

Max Activating Token Index: 837

Text #4

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1767. Min Act: -0.0002

Data Index: 1610485 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1522514 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1591614 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1330. Min Act: -0.0002

Data Index: 836311 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1567. Min Act: -0.0002

Data Index: 209818 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1332263 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1649214 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1128. Min Act: -0.0002

Data Index: 817397 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1156. Min Act: -0.0002

Data Index: 1378264 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1367577 (Python Code)

Max Activating Token Index: 669

Text #14

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1230. Min Act: -0.0002

Data Index: 1322859 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1277. Min Act: -0.0002

Data Index: 1642608 (Python Code)

Max Activating Token Index: 864

Text #16

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1380. Min Act: -0.0002

Data Index: 941713 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1621657 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1602331 (Python Code)

Max Activating Token Index: 930

Text #19

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1299. Min Act: -0.0002

Data Index: 493371 (C4 (Web Text))

Max Activating Token Index: 311