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

Dataset: The Pile

Neuron 3044 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: 0.2246. Min Range: -0.2246

Max Act: 0.2246. Min Act: -0.0000

Data Index: 231363 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1746. Min Act: -0.0000

Data Index: 521465 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2074. Min Act: -0.0000

Data Index: 100284 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1983211 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1933166 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1056418 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1539. Min Act: -0.0000

Data Index: 914892 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1422. Min Act: -0.0000

Data Index: 901351 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1764. Min Act: -0.0000

Data Index: 102843 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1815465 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1614. Min Act: -0.0000

Data Index: 496106 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1714459 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1185918 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1159829 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1763313 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1633588 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1509680 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1567537 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1848675 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1746042 (The Pile)

Max Activating Token Index: 762