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

Dataset: The Pile

Neuron 944 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: 0.7205. Min Range: -0.7205

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1129713 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6404. Min Act: -0.0000

Data Index: 274524 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1534379 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1379716 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1092814 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5446. Min Act: -0.0000

Data Index: 838054 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1415891 (The Pile)

Max Activating Token Index: 648

Text #7

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5346. Min Act: -0.0000

Data Index: 776923 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5011. Min Act: -0.0000

Data Index: 589899 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5543. Min Act: -0.0000

Data Index: 366455 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5313. Min Act: -0.0000

Data Index: 743387 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5138. Min Act: -0.0000

Data Index: 710944 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1438615 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4716. Min Act: -0.0000

Data Index: 278496 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4860. Min Act: -0.0000

Data Index: 893575 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4618. Min Act: -0.0000

Data Index: 527798 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1835248 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1992186 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4541. Min Act: -0.0000

Data Index: 266461 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4431. Min Act: -0.0000

Data Index: 158055 (The Pile)

Max Activating Token Index: 780