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

Dataset: The Pile

Neuron 2018 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: 1.1674. Min Range: -1.1674

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1145738 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.1674. Min Act: 0.0000

Data Index: 848653 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9391. Min Act: 0.0000

Data Index: 251612 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9646. Min Act: -0.0000

Data Index: 691963 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0160. Min Act: -0.0000

Data Index: 721246 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0441. Min Act: -0.0000

Data Index: 406680 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1721983 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0584. Min Act: -0.0000

Data Index: 783668 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1468156 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0727. Min Act: -0.0000

Data Index: 664100 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1542949 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1509618 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9072. Min Act: -0.0000

Data Index: 271891 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1888013 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1698561 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1207246 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9841. Min Act: 0.0000

Data Index: 982733 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9676. Min Act: -0.0000

Data Index: 494800 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1971143 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1379958 (The Pile)

Max Activating Token Index: 828