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

Dataset: The Pile

Neuron 4649 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: 0.6806. Min Range: -0.6806

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1787050 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6421. Min Act: -0.0000

Data Index: 316629 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1827251 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5884. Min Act: -0.0000

Data Index: 46220 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1412371 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1421509 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1751220 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1005517 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1411023 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5621. Min Act: -0.0000

Data Index: 165573 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5734. Min Act: -0.0000

Data Index: 936769 (The Pile)

Max Activating Token Index: 287

Text #11

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5315. Min Act: -0.0000

Data Index: 659274 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5259. Min Act: -0.0000

Data Index: 128117 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4621. Min Act: -0.0000

Data Index: 980226 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1173284 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5574. Min Act: -0.0000

Data Index: 768565 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1263694 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4787. Min Act: -0.0000

Data Index: 952394 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5085. Min Act: -0.0000

Data Index: 287726 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5422. Min Act: -0.0000

Data Index: 165544 (The Pile)

Max Activating Token Index: 650