Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2137 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1749. Min Act: -0.0001

Data Index: 79313 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1750. Min Act: -0.0001

Data Index: 344882 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1531. Min Act: -0.0001

Data Index: 473668 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1286449 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1510764 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1423. Min Act: -0.0001

Data Index: 498693 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1369. Min Act: -0.0001

Data Index: 927546 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1402063 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1262. Min Act: -0.0001

Data Index: 805258 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1392423 (Python Code)

Max Activating Token Index: 444

Text #10

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1103749 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1322. Min Act: -0.0001

Data Index: 542916 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1161. Min Act: -0.0001

Data Index: 511782 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1563702 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1248. Min Act: -0.0001

Data Index: 800009 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1205. Min Act: -0.0001

Data Index: 233007 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1099283 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1195. Min Act: -0.0001

Data Index: 655213 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1197. Min Act: -0.0001

Data Index: 707034 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1103122 (C4 (Web Text))

Max Activating Token Index: 861