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

Dataset: The Pile

Neuron 2468 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1533079 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7082. Min Act: -0.0000

Data Index: 726103 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7003. Min Act: -0.0000

Data Index: 481337 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1156124 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7480. Min Act: -0.0000

Data Index: 611677 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6761. Min Act: -0.0000

Data Index: 821203 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6193. Min Act: -0.0000

Data Index: 529151 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1425859 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1827354 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1058592 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1110937 (The Pile)

Max Activating Token Index: 197

Text #11

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1684036 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1060739 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1266618 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1966383 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6085. Min Act: -0.0000

Data Index: 129359 (The Pile)

Max Activating Token Index: 375

Text #16

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1674681 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1936481 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1048589 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.5755. Min Act: -0.0000

Data Index: 887528 (The Pile)

Max Activating Token Index: 325