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

Dataset: The Pile

Neuron 895 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.0602. Min Range: -5.0602

Max Act: 5.0602. Min Act: -0.0000

Data Index: 1372212 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.7654. Min Act: -0.0000

Data Index: 1080071 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.5656. Min Act: -0.0000

Data Index: 1054207 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.6751. Min Act: -0.0000

Data Index: 1297784 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.3083. Min Act: -0.0000

Data Index: 659292 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.2920. Min Act: -0.0000

Data Index: 738092 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.4372. Min Act: -0.0000

Data Index: 1407819 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.3989. Min Act: -0.0000

Data Index: 140011 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.0471. Min Act: -0.0000

Data Index: 1680328 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.2060. Min Act: -0.0000

Data Index: 168363 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.0226. Min Act: -0.0000

Data Index: 740899 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 5.0602. Min Range: -5.0602

Max Act: 3.8571. Min Act: -0.0000

Data Index: 1280421 (The Pile)

Max Activating Token Index: 806

Text #12

Max Range: 5.0602. Min Range: -5.0602

Max Act: 3.9928. Min Act: -0.0000

Data Index: 1860571 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.1466. Min Act: -0.0000

Data Index: 250716 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 5.0602. Min Range: -5.0602

Max Act: 3.9671. Min Act: -0.0000

Data Index: 439894 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 5.0602. Min Range: -5.0602

Max Act: 3.9457. Min Act: -0.0000

Data Index: 617017 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 5.0602. Min Range: -5.0602

Max Act: 3.9891. Min Act: -0.0000

Data Index: 792735 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 5.0602. Min Range: -5.0602

Max Act: 4.0804. Min Act: -0.0000

Data Index: 509468 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 5.0602. Min Range: -5.0602

Max Act: 3.8932. Min Act: -0.0000

Data Index: 1523003 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 5.0602. Min Range: -5.0602

Max Act: 3.8571. Min Act: -0.0000

Data Index: 443407 (The Pile)

Max Activating Token Index: 247