Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1705 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7406. Min Act: -0.0001

Data Index: 813719 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7396. Min Act: -0.0000

Data Index: 283745 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6541. Min Act: -0.0000

Data Index: 186812 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6067. Min Act: -0.0001

Data Index: 586715 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6200. Min Act: -0.0000

Data Index: 284582 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1269712 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5536. Min Act: -0.0000

Data Index: 780510 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6082. Min Act: -0.0000

Data Index: 973099 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1253304 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5465. Min Act: -0.0000

Data Index: 588272 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5362. Min Act: -0.0001

Data Index: 639894 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5345. Min Act: -0.0001

Data Index: 1581242 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5249. Min Act: -0.0001

Data Index: 1206370 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1351674 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1059044 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1189613 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.4775. Min Act: -0.0001

Data Index: 481944 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1355059 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.4756. Min Act: -0.0001

Data Index: 498378 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.4833. Min Act: -0.0001

Data Index: 627986 (C4 (Web Text))

Max Activating Token Index: 105