Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3706 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1987. Min Act: -0.0001

Data Index: 838004 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1254722 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1241603 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1880. Min Act: -0.0001

Data Index: 623474 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1731. Min Act: -0.0001

Data Index: 653938 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1872. Min Act: -0.0001

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1318632 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1642. Min Act: -0.0001

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1496. Min Act: -0.0001

Data Index: 503734 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1056587 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1437. Min Act: -0.0001

Data Index: 599223 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1110779 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1360. Min Act: -0.0001

Data Index: 665462 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1291. Min Act: -0.0001

Data Index: 382747 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1358. Min Act: -0.0001

Data Index: 683929 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1034192 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1121. Min Act: -0.0000

Data Index: 502670 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1240. Min Act: -0.0001

Data Index: 873351 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1059. Min Act: -0.0001

Data Index: 612491 (C4 (Web Text))

Max Activating Token Index: 814