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

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

Neuron 4859 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1603648 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1578989 (Python Code)

Max Activating Token Index: 938

Text #2

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1617468 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2198. Min Act: 0.0000

Data Index: 1647951 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1887. Min Act: 0.0000

Data Index: 1534247 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1477577 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1453525 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1570032 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1513258 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1402730 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1507887 (Python Code)

Max Activating Token Index: 634

Text #11

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1444674 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9774. Min Act: 0.0000

Data Index: 1418044 (Python Code)

Max Activating Token Index: 81

Text #13

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9970. Min Act: 0.0000

Data Index: 1616280 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1607033 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1438538 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1513313 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1564683 (Python Code)

Max Activating Token Index: 388

Text #18

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1493550 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1550082 (Python Code)

Max Activating Token Index: 939