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

Dataset: The Pile

Neuron 1260 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: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0000

Data Index: 788888 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1521257 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0957. Min Act: -0.0000

Data Index: 452473 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0996. Min Act: -0.0000

Data Index: 876714 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0944. Min Act: -0.0000

Data Index: 453587 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0900. Min Act: -0.0000

Data Index: 319458 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1695814 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1444391 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0904. Min Act: -0.0000

Data Index: 729822 (The Pile)

Max Activating Token Index: 845

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0930. Min Act: -0.0000

Data Index: 692276 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0880. Min Act: -0.0000

Data Index: 212351 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1398158 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1005381 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1519605 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1778883 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0758. Min Act: -0.0000

Data Index: 112380 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1213941 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0713. Min Act: -0.0000

Data Index: 374692 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1197330 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1773898 (The Pile)

Max Activating Token Index: 851