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

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

Neuron 242 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2392. Min Act: -0.0003

Data Index: 989014 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2218. Min Act: -0.0003

Data Index: 141438 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2321. Min Act: -0.0003

Data Index: 569665 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2350. Min Act: -0.0003

Data Index: 1352063 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2341. Min Act: -0.0003

Data Index: 924783 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2001. Min Act: -0.0003

Data Index: 534692 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2202. Min Act: -0.0003

Data Index: 486469 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2067. Min Act: -0.0003

Data Index: 390088 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1931. Min Act: -0.0003

Data Index: 481260 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2011. Min Act: -0.0003

Data Index: 974926 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2179. Min Act: -0.0003

Data Index: 230298 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2001. Min Act: -0.0003

Data Index: 1247676 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1926. Min Act: -0.0003

Data Index: 798990 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1774. Min Act: -0.0003

Data Index: 403881 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1897. Min Act: -0.0003

Data Index: 442069 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1974. Min Act: -0.0003

Data Index: 371334 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1560. Min Act: -0.0003

Data Index: 991399 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1725. Min Act: -0.0003

Data Index: 1078323 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1341591 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1525. Min Act: -0.0003

Data Index: 816507 (C4 (Web Text))

Max Activating Token Index: 798