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

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

Neuron 998 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: 3.3822. Min Range: -3.3822

Max Act: 3.3822. Min Act: -0.0001

Data Index: 1389099 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 3.3822. Min Range: -3.3822

Max Act: 3.1770. Min Act: -0.0001

Data Index: 1546097 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.8380. Min Act: -0.0001

Data Index: 1642493 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.7959. Min Act: -0.0001

Data Index: 1627702 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.8602. Min Act: -0.0001

Data Index: 1479586 (Python Code)

Max Activating Token Index: 938

Text #5

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.5934. Min Act: -0.0001

Data Index: 1419563 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.3471. Min Act: -0.0001

Data Index: 1387679 (Python Code)

Max Activating Token Index: 905

Text #7

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.5790. Min Act: -0.0001

Data Index: 1386371 (Python Code)

Max Activating Token Index: 976

Text #8

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.6363. Min Act: -0.0001

Data Index: 1521845 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.5759. Min Act: -0.0001

Data Index: 1489828 (Python Code)

Max Activating Token Index: 974

Text #10

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.5289. Min Act: -0.0001

Data Index: 1450987 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.2220. Min Act: -0.0001

Data Index: 1459872 (Python Code)

Max Activating Token Index: 772

Text #12

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.6535. Min Act: -0.0001

Data Index: 1475131 (Python Code)

Max Activating Token Index: 1011

Text #13

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.2618. Min Act: -0.0001

Data Index: 1625303 (Python Code)

Max Activating Token Index: 797

Text #14

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.4302. Min Act: -0.0001

Data Index: 1371503 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.3726. Min Act: -0.0001

Data Index: 1400771 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.2159. Min Act: -0.0001

Data Index: 1523071 (Python Code)

Max Activating Token Index: 767

Text #17

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.2555. Min Act: -0.0001

Data Index: 1638381 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.3607. Min Act: -0.0001

Data Index: 1544723 (Python Code)

Max Activating Token Index: 747

Text #19

Max Range: 3.3822. Min Range: -3.3822

Max Act: 2.3595. Min Act: -0.0001

Data Index: 1509919 (Python Code)

Max Activating Token Index: 18