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

Dataset: The Pile

Neuron 3068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2485. Min Range: -1.2485

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1937241 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 1.2485. Min Range: -1.2485

Max Act: 1.0289. Min Act: -0.0000

Data Index: 921790 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 1.2485. Min Range: -1.2485

Max Act: 1.1510. Min Act: -0.0000

Data Index: 191466 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 1.2485. Min Range: -1.2485

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1932278 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.9202. Min Act: -0.0000

Data Index: 193120 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.9810. Min Act: -0.0000

Data Index: 56191 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1538644 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1121432 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1114220 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1466258 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1601856 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7673. Min Act: -0.0000

Data Index: 375617 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1930890 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7088. Min Act: -0.0000

Data Index: 581573 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1596367 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7014. Min Act: -0.0000

Data Index: 618937 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.6858. Min Act: -0.0000

Data Index: 614252 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7298. Min Act: -0.0000

Data Index: 838902 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.6592. Min Act: -0.0000

Data Index: 400059 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 1.2485. Min Range: -1.2485

Max Act: 0.7464. Min Act: -0.0000

Data Index: 470 (The Pile)

Max Activating Token Index: 157