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

Dataset: The Pile

Neuron 4415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.3376. Min Act: -0.0000

Data Index: 635142 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.2675. Min Act: -0.0000

Data Index: 351727 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.3112. Min Act: -0.0000

Data Index: 578838 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.2304. Min Act: -0.0000

Data Index: 82936 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1682. Min Act: -0.0000

Data Index: 735216 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1879451 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1812. Min Act: -0.0000

Data Index: 572192 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1615. Min Act: -0.0000

Data Index: 767630 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1476314 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1363. Min Act: -0.0000

Data Index: 457251 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1272. Min Act: -0.0000

Data Index: 324823 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1647577 (The Pile)

Max Activating Token Index: 556

Text #12

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1613877 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1753033 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9245. Min Act: -0.0000

Data Index: 537784 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0691. Min Act: -0.0000

Data Index: 573544 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0445. Min Act: -0.0000

Data Index: 929683 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0196. Min Act: -0.0000

Data Index: 86315 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0307. Min Act: -0.0000

Data Index: 590641 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1182876 (The Pile)

Max Activating Token Index: 472