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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2894 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4225. Min Act: -0.0004

Data Index: 717443 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3752. Min Act: -0.0004

Data Index: 1200734 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3873. Min Act: -0.0004

Data Index: 719411 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3852. Min Act: -0.0004

Data Index: 558784 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3694. Min Act: -0.0004

Data Index: 450648 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3672. Min Act: -0.0004

Data Index: 1217085 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3432. Min Act: -0.0004

Data Index: 151507 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4037. Min Act: -0.0004

Data Index: 942486 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3864. Min Act: -0.0004

Data Index: 358178 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3819. Min Act: -0.0004

Data Index: 498900 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3685. Min Act: -0.0004

Data Index: 1088871 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3668. Min Act: -0.0004

Data Index: 957919 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3899. Min Act: -0.0004

Data Index: 676486 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3427. Min Act: -0.0004

Data Index: 134101 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3634. Min Act: -0.0004

Data Index: 430599 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3274. Min Act: -0.0004

Data Index: 1054645 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3487. Min Act: -0.0004

Data Index: 507528 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3724. Min Act: -0.0004

Data Index: 178321 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3606. Min Act: -0.0004

Data Index: 935947 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3478. Min Act: -0.0004

Data Index: 668455 (C4 (Web Text))

Max Activating Token Index: 563