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

Dataset: The Pile

Neuron 941 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1513838 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.7388. Min Act: -0.0000

Data Index: 303910 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1561799 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1744276 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1233857 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1132760 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6537. Min Act: -0.0000

Data Index: 777958 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1446487 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1068926 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1080380 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6351. Min Act: -0.0000

Data Index: 964640 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1261133 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6080. Min Act: -0.0000

Data Index: 401863 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1799584 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1165039 (The Pile)

Max Activating Token Index: 900

Text #15

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1522966 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.5349. Min Act: -0.0000

Data Index: 881519 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1781491 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.5921. Min Act: -0.0001

Data Index: 862913 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.8689. Min Range: -0.8689

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1949094 (The Pile)

Max Activating Token Index: 157