Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 490 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.1881. Min Range: -1.1881

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1840157 (The Pile)

Max Activating Token Index: 949

Text #1

Max Range: 1.1881. Min Range: -1.1881

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1022719 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 1.1881. Min Range: -1.1881

Max Act: 1.0634. Min Act: -0.0001

Data Index: 1255234 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 1.1881. Min Range: -1.1881

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1118104 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8894. Min Act: -0.0000

Data Index: 143238 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1161042 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9487. Min Act: -0.0000

Data Index: 323423 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8352. Min Act: -0.0000

Data Index: 587195 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1776792 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1526505 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8428. Min Act: -0.0000

Data Index: 77743 (The Pile)

Max Activating Token Index: 702

Text #11

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.7258. Min Act: -0.0000

Data Index: 550702 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8409. Min Act: -0.0000

Data Index: 630590 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1042454 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1849828 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1979818 (The Pile)

Max Activating Token Index: 682

Text #16

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8598. Min Act: -0.0000

Data Index: 38033 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.7413. Min Act: -0.0000

Data Index: 577242 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1509351 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.7390. Min Act: -0.0001

Data Index: 39831 (The Pile)

Max Activating Token Index: 695