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

Dataset: The Pile

Neuron 3889 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: 0.6216. Min Range: -0.6216

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1886873 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1799248 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1164320 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1025465 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1830553 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5137. Min Act: -0.0000

Data Index: 774050 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1561642 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4858. Min Act: -0.0000

Data Index: 890464 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1106310 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3848. Min Act: -0.0000

Data Index: 1079821 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1174102 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1902102 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1831938 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1242336 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3383. Min Act: -0.0000

Data Index: 670877 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1024774 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3736. Min Act: -0.0000

Data Index: 77866 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4350. Min Act: -0.0000

Data Index: 368117 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1669575 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4418. Min Act: -0.0000

Data Index: 575067 (The Pile)

Max Activating Token Index: 724