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

Dataset: The Pile

Neuron 3687 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: 0.2033. Min Range: -0.2033

Max Act: 0.1973. Min Act: -0.0000

Data Index: 334210 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1234540 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1896810 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1344637 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1849794 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1087754 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1418385 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1759. Min Act: -0.0000

Data Index: 880247 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1769. Min Act: -0.0000

Data Index: 179045 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1673. Min Act: -0.0000

Data Index: 744605 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1497. Min Act: -0.0000

Data Index: 648938 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1395944 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1547. Min Act: -0.0000

Data Index: 351877 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1610. Min Act: -0.0000

Data Index: 856510 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1549. Min Act: -0.0000

Data Index: 479888 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1585. Min Act: -0.0000

Data Index: 656381 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1636. Min Act: -0.0000

Data Index: 748759 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1341114 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1555. Min Act: -0.0000

Data Index: 672930 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1157277 (The Pile)

Max Activating Token Index: 841