Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4476 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.4808. Min Act: -0.0000

Data Index: 125119 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.0571. Min Act: -0.0000

Data Index: 596347 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.0664. Min Act: -0.0000

Data Index: 876327 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1069679 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1000798 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.9180. Min Act: -0.0000

Data Index: 987325 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1055039 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.8673. Min Act: -0.0000

Data Index: 611445 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.8507. Min Act: -0.0000

Data Index: 639164 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.8224. Min Act: -0.0000

Data Index: 111851 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1171205 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.8647. Min Act: -0.0000

Data Index: 880925 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1806771 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1794479 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1918366 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.7617. Min Act: -0.0000

Data Index: 915102 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1085036 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1555487 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1618286 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1376858 (The Pile)

Max Activating Token Index: 326