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

Dataset: The Pile

Neuron 3326 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: 3.2675. Min Range: -3.2675

Max Act: 3.2675. Min Act: -0.0000

Data Index: 1816079 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.9026. Min Act: -0.0000

Data Index: 1138093 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.8240. Min Act: -0.0000

Data Index: 909761 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.8295. Min Act: -0.0000

Data Index: 71877 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.5660. Min Act: -0.0000

Data Index: 840483 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.3557. Min Act: -0.0000

Data Index: 1753056 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.4215. Min Act: -0.0000

Data Index: 509192 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.2021. Min Act: -0.0000

Data Index: 1282930 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.4788. Min Act: -0.0000

Data Index: 943149 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.3766. Min Act: -0.0000

Data Index: 576729 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.3345. Min Act: -0.0000

Data Index: 1503054 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.1952. Min Act: -0.0000

Data Index: 1364615 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.3367. Min Act: -0.0000

Data Index: 1213794 (The Pile)

Max Activating Token Index: 957

Text #13

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.0668. Min Act: -0.0000

Data Index: 1216821 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1922089 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.0655. Min Act: -0.0000

Data Index: 88912 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.0029. Min Act: -0.0000

Data Index: 1788124 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.3238. Min Act: -0.0000

Data Index: 439492 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.0514. Min Act: -0.0000

Data Index: 311056 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 3.2675. Min Range: -3.2675

Max Act: 2.3742. Min Act: -0.0000

Data Index: 1928516 (The Pile)

Max Activating Token Index: 1013