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

Dataset: The Pile

Neuron 2955 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: 1.4638. Min Range: -1.4638

Max Act: 1.3555. Min Act: -0.0000

Data Index: 1379292 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.4638. Min Act: -0.0000

Data Index: 1373745 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.3208. Min Act: -0.0000

Data Index: 516789 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1520447 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.2090. Min Act: -0.0000

Data Index: 393686 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.2043. Min Act: -0.0000

Data Index: 517358 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.3396. Min Act: -0.0000

Data Index: 503606 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1158924 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1478539 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1776. Min Act: -0.0000

Data Index: 447114 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1354957 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1662390 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1079902 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1220. Min Act: -0.0000

Data Index: 697686 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1923. Min Act: -0.0000

Data Index: 996551 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.0815. Min Act: -0.0000

Data Index: 840574 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1412. Min Act: -0.0000

Data Index: 579067 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.0255. Min Act: -0.0000

Data Index: 594505 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 1.4638. Min Range: -1.4638

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1008487 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 1.4638. Min Range: -1.4638

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1428419 (The Pile)

Max Activating Token Index: 26