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

Dataset: The Pile

Neuron 2815 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: 1.8435. Min Range: -1.8435

Max Act: 1.8435. Min Act: -0.0000

Data Index: 101609 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.6674. Min Act: -0.0000

Data Index: 531680 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5658. Min Act: -0.0000

Data Index: 1520412 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5589. Min Act: -0.0000

Data Index: 219665 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.6097. Min Act: -0.0000

Data Index: 452326 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5455. Min Act: -0.0001

Data Index: 1713120 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5903. Min Act: -0.0000

Data Index: 781012 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5717. Min Act: -0.0000

Data Index: 411104 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5045. Min Act: -0.0000

Data Index: 205536 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5514. Min Act: -0.0000

Data Index: 312919 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5436. Min Act: -0.0000

Data Index: 25126 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5416. Min Act: -0.0000

Data Index: 939535 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5482. Min Act: -0.0000

Data Index: 485804 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1445062 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.4085. Min Act: -0.0000

Data Index: 1174775 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1468952 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.4764. Min Act: -0.0000

Data Index: 533386 (The Pile)

Max Activating Token Index: 749

Text #17

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.4172. Min Act: -0.0000

Data Index: 252296 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.4319. Min Act: -0.0000

Data Index: 1332981 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 1.8435. Min Range: -1.8435

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1713201 (The Pile)

Max Activating Token Index: 383