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

Dataset: The Pile

Neuron 2908 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: 0.6817. Min Range: -0.6817

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1471477 (The Pile)

Max Activating Token Index: 481

Text #1

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6789. Min Act: -0.0000

Data Index: 64328 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6708. Min Act: 0.0000

Data Index: 1314075 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6220. Min Act: -0.0000

Data Index: 732278 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5757. Min Act: -0.0000

Data Index: 818932 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5561. Min Act: -0.0000

Data Index: 276358 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4746. Min Act: -0.0000

Data Index: 905682 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1256066 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4459. Min Act: -0.0000

Data Index: 58092 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1413574 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1344326 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4519. Min Act: -0.0000

Data Index: 774567 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1900451 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4542. Min Act: -0.0000

Data Index: 479371 (The Pile)

Max Activating Token Index: 966

Text #14

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4589. Min Act: 0.0000

Data Index: 1196866 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4310. Min Act: -0.0000

Data Index: 981914 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1135024 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4395. Min Act: -0.0000

Data Index: 741366 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4306. Min Act: -0.0000

Data Index: 968573 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1629611 (The Pile)

Max Activating Token Index: 568