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

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

Neuron 2046 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.6323. Min Act: -0.0001

Data Index: 332704 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4442. Min Act: -0.0001

Data Index: 344034 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2833. Min Act: -0.0001

Data Index: 368763 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.3036. Min Act: -0.0001

Data Index: 632441 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.3023. Min Act: -0.0001

Data Index: 599319 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2071. Min Act: -0.0001

Data Index: 427363 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2150. Min Act: -0.0001

Data Index: 525645 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2422. Min Act: -0.0001

Data Index: 402366 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2226. Min Act: -0.0001

Data Index: 171517 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1957. Min Act: -0.0001

Data Index: 339937 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2502. Min Act: -0.0001

Data Index: 1283281 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1701. Min Act: -0.0001

Data Index: 376502 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1664. Min Act: -0.0001

Data Index: 528942 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2207. Min Act: -0.0001

Data Index: 109060 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1181. Min Act: -0.0001

Data Index: 82201 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1222. Min Act: -0.0001

Data Index: 373660 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.0531. Min Act: -0.0001

Data Index: 681601 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1258. Min Act: -0.0001

Data Index: 19836 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1042913 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1461. Min Act: -0.0001

Data Index: 369719 (C4 (Web Text))

Max Activating Token Index: 546