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

Dataset: The Pile

Neuron 138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.4480. Min Act: -0.0000

Data Index: 780050 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.4570. Min Act: 0.0000

Data Index: 1217251 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.4390. Min Act: -0.0000

Data Index: 198063 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.4386. Min Act: 0.0000

Data Index: 1434065 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1270697 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3991. Min Act: 0.0000

Data Index: 921577 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3862. Min Act: -0.0000

Data Index: 489541 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1568568 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3919. Min Act: -0.0000

Data Index: 39400 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1570659 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1509331 (The Pile)

Max Activating Token Index: 660

Text #11

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3681. Min Act: -0.0000

Data Index: 718200 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3926. Min Act: -0.0000

Data Index: 954943 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1742891 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1898882 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1994255 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1170771 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1814490 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3464. Min Act: -0.0000

Data Index: 720512 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1297214 (The Pile)

Max Activating Token Index: 704