Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3190 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.7517. Min Act: -0.0000

Data Index: 1625696 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.7407. Min Act: -0.0000

Data Index: 1558993 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5420. Min Act: -0.0000

Data Index: 822583 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5326. Min Act: -0.0000

Data Index: 103453 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1277650 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1107743 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1102804 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1809. Min Act: -0.0000

Data Index: 264168 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1560. Min Act: -0.0000

Data Index: 163242 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1499471 (Python Code)

Max Activating Token Index: 486

Text #10

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1189. Min Act: -0.0000

Data Index: 828435 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1023. Min Act: -0.0000

Data Index: 226998 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1317018 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1491. Min Act: -0.0000

Data Index: 391016 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1387492 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0777. Min Act: -0.0000

Data Index: 99747 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0580. Min Act: -0.0000

Data Index: 163559 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1253460 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1268773 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1066983 (C4 (Web Text))

Max Activating Token Index: 591