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

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

Neuron 2043 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3581. Min Act: -0.0000

Data Index: 339260 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3387. Min Act: -0.0000

Data Index: 588432 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3466. Min Act: -0.0000

Data Index: 669839 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3474. Min Act: -0.0000

Data Index: 909668 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3232. Min Act: -0.0000

Data Index: 810243 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3344. Min Act: -0.0001

Data Index: 308872 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3216. Min Act: -0.0001

Data Index: 912228 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3395. Min Act: -0.0000

Data Index: 607936 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1230300 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2825. Min Act: -0.0000

Data Index: 386865 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2879. Min Act: -0.0000

Data Index: 402302 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1142633 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2866. Min Act: -0.0000

Data Index: 729677 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2608. Min Act: -0.0000

Data Index: 876314 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1252083 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2497. Min Act: -0.0001

Data Index: 390940 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2752. Min Act: -0.0000

Data Index: 995895 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2731. Min Act: -0.0000

Data Index: 255687 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1215703 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1268274 (C4 (Web Text))

Max Activating Token Index: 902