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

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

Neuron 3293 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6311. Min Range: -4.6311

Max Act: 4.6311. Min Act: -0.0000

Data Index: 1339932 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.9493. Min Act: -0.0000

Data Index: 40096 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 4.6311. Min Range: -4.6311

Max Act: 4.1332. Min Act: -0.0000

Data Index: 91912 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 4.6311. Min Range: -4.6311

Max Act: 4.2422. Min Act: -0.0000

Data Index: 517261 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 4.6311. Min Range: -4.6311

Max Act: 4.1415. Min Act: -0.0000

Data Index: 166123 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.6531. Min Act: -0.0000

Data Index: 1126253 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.7918. Min Act: -0.0000

Data Index: 1320742 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.6022. Min Act: -0.0000

Data Index: 1164005 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.7603. Min Act: -0.0000

Data Index: 432553 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.5959. Min Act: -0.0000

Data Index: 582758 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.7323. Min Act: -0.0000

Data Index: 171249 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.8398. Min Act: -0.0000

Data Index: 975117 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.6744. Min Act: -0.0000

Data Index: 361244 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.6506. Min Act: -0.0000

Data Index: 97197 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.6157. Min Act: -0.0000

Data Index: 98607 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.2769. Min Act: -0.0001

Data Index: 639190 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.5188. Min Act: -0.0000

Data Index: 930442 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.5221. Min Act: -0.0000

Data Index: 768315 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.5242. Min Act: -0.0000

Data Index: 928304 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 4.6311. Min Range: -4.6311

Max Act: 3.5343. Min Act: -0.0000

Data Index: 874233 (C4 (Web Text))

Max Activating Token Index: 269