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

Dataset: The Pile

Neuron 3269 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1364818 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1563535 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2571. Min Act: -0.0000

Data Index: 54846 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2356. Min Act: -0.0000

Data Index: 487623 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1219542 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1833018 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1958314 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2312. Min Act: -0.0000

Data Index: 3088 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2345. Min Act: -0.0000

Data Index: 810454 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1117643 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2260. Min Act: -0.0000

Data Index: 314458 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1475788 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2065. Min Act: -0.0000

Data Index: 64121 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2053. Min Act: -0.0000

Data Index: 294949 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2116. Min Act: -0.0000

Data Index: 270062 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1358440 (The Pile)

Max Activating Token Index: 505

Text #16

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1406444 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1454098 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1221246 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1180858 (The Pile)

Max Activating Token Index: 444