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

Dataset: The Pile

Neuron 3710 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: 0.7399. Min Range: -0.7399

Max Act: 0.7399. Min Act: -0.0000

Data Index: 690573 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.5141. Min Act: -0.0000

Data Index: 867875 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1550263 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.5464. Min Act: -0.0000

Data Index: 563500 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1798585 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4917. Min Act: -0.0000

Data Index: 311992 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1729027 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4794. Min Act: -0.0000

Data Index: 532265 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1394318 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4503. Min Act: -0.0000

Data Index: 499454 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1581877 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1095312 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4456. Min Act: -0.0000

Data Index: 352592 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4681. Min Act: -0.0000

Data Index: 775347 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1809423 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4696. Min Act: -0.0000

Data Index: 924656 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1695063 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1727003 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4349. Min Act: -0.0000

Data Index: 87455 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1236211 (The Pile)

Max Activating Token Index: 76