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

Dataset: The Pile

Neuron 871 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0358. Min Range: -1.0358

Max Act: 1.0358. Min Act: -0.0000

Data Index: 504283 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.9328. Min Act: -0.0000

Data Index: 124381 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.9112. Min Act: -0.0000

Data Index: 125337 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1672827 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7454. Min Act: -0.0000

Data Index: 928147 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1505127 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1768187 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1530240 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7185. Min Act: -0.0000

Data Index: 665892 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1619846 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1060297 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6387. Min Act: -0.0000

Data Index: 299332 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1632700 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1990842 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7058. Min Act: -0.0000

Data Index: 685845 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7658. Min Act: -0.0000

Data Index: 664861 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6352. Min Act: -0.0000

Data Index: 622443 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1637322 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1132412 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6147. Min Act: -0.0000

Data Index: 974667 (The Pile)

Max Activating Token Index: 345