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

Dataset: The Pile

Neuron 3823 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1505740 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1885563 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1453203 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1009918 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.2380. Min Act: -0.0000

Data Index: 58667 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1904546 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9579. Min Act: -0.0000

Data Index: 477934 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9684. Min Act: -0.0000

Data Index: 77218 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0070. Min Act: -0.0000

Data Index: 269628 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1736695 (The Pile)

Max Activating Token Index: 461

Text #10

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1655972 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1867128 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1514123 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9699. Min Act: -0.0000

Data Index: 894585 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9506. Min Act: -0.0000

Data Index: 26223 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1402892 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1079482 (The Pile)

Max Activating Token Index: 670

Text #17

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1422797 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1395722 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1183649 (The Pile)

Max Activating Token Index: 924