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

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

Neuron 3789 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2447. Min Act: -0.0000

Data Index: 937911 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1325402 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1845. Min Act: -0.0000

Data Index: 886329 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1867. Min Act: -0.0000

Data Index: 137757 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1116426 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1211870 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1447. Min Act: -0.0000

Data Index: 609631 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1467352 (Python Code)

Max Activating Token Index: 132

Text #8

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1297528 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1284. Min Act: -0.0000

Data Index: 621085 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1270. Min Act: -0.0000

Data Index: 812240 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1284604 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1111916 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1380917 (Python Code)

Max Activating Token Index: 816

Text #14

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1618520 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1185. Min Act: -0.0000

Data Index: 716748 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1188. Min Act: -0.0000

Data Index: 185493 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1025032 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1616539 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1160872 (C4 (Web Text))

Max Activating Token Index: 433