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

Dataset: The Pile

Neuron 3022 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: 1.2134. Min Range: -1.2134

Max Act: 1.2134. Min Act: -0.0000

Data Index: 763301 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 1.2134. Min Range: -1.2134

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1702993 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 1.2134. Min Range: -1.2134

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1800451 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.9778. Min Act: -0.0000

Data Index: 515005 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8860. Min Act: 0.0000

Data Index: 335347 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.9408. Min Act: -0.0000

Data Index: 320384 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1910537 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7847. Min Act: -0.0000

Data Index: 739179 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7780. Min Act: -0.0000

Data Index: 510579 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1432390 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8301. Min Act: -0.0000

Data Index: 769418 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.6969. Min Act: -0.0000

Data Index: 836459 (The Pile)

Max Activating Token Index: 720

Text #12

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.6900. Min Act: -0.0000

Data Index: 370918 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1442812 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1737040 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1822447 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.6672. Min Act: -0.0000

Data Index: 652889 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7708. Min Act: -0.0000

Data Index: 724225 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1319925 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1554591 (The Pile)

Max Activating Token Index: 1000