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

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

Neuron 861 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: 1.9202. Min Range: -1.9202

Max Act: 1.9202. Min Act: -0.0000

Data Index: 1307215 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.8992. Min Act: -0.0000

Data Index: 327909 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.8546. Min Act: -0.0000

Data Index: 207688 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6331. Min Act: -0.0000

Data Index: 647040 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.5967. Min Act: -0.0000

Data Index: 459199 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.5118. Min Act: -0.0001

Data Index: 831063 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6816. Min Act: -0.0000

Data Index: 1561633 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6496. Min Act: -0.0000

Data Index: 120704 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6299. Min Act: -0.0000

Data Index: 1128702 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.5301. Min Act: -0.0000

Data Index: 1539919 (Python Code)

Max Activating Token Index: 1007

Text #10

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6948. Min Act: -0.0000

Data Index: 935316 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1306876 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6035. Min Act: -0.0001

Data Index: 459797 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1167805 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.5957. Min Act: -0.0000

Data Index: 1140986 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6750. Min Act: -0.0001

Data Index: 558605 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1631165 (Python Code)

Max Activating Token Index: 298

Text #17

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6625. Min Act: -0.0000

Data Index: 438466 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.5855. Min Act: -0.0000

Data Index: 767980 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 1.9202. Min Range: -1.9202

Max Act: 1.6551. Min Act: -0.0000

Data Index: 188399 (C4 (Web Text))

Max Activating Token Index: 988