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

Dataset: The Pile

Neuron 3986 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: 0.9796. Min Range: -0.9796

Max Act: 0.9796. Min Act: 0.0000

Data Index: 201635 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1563865 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8052. Min Act: 0.0000

Data Index: 1096981 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7579. Min Act: 0.0000

Data Index: 761731 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7023. Min Act: 0.0000

Data Index: 1945293 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1958972 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6740. Min Act: 0.0000

Data Index: 314832 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7397. Min Act: -0.0000

Data Index: 675833 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6757. Min Act: 0.0000

Data Index: 568210 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6538. Min Act: 0.0000

Data Index: 1478256 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6306. Min Act: 0.0000

Data Index: 535 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6427. Min Act: 0.0000

Data Index: 534010 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6272. Min Act: 0.0000

Data Index: 1994747 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6405. Min Act: 0.0000

Data Index: 495360 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6581. Min Act: 0.0000

Data Index: 352878 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1718618 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6130. Min Act: -0.0000

Data Index: 429669 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6471. Min Act: 0.0000

Data Index: 1835880 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6565. Min Act: -0.0000

Data Index: 823260 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6287. Min Act: 0.0000

Data Index: 642620 (The Pile)

Max Activating Token Index: 232