Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 51 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0817. Min Range: -4.0817

Max Act: 3.9861. Min Act: -0.0000

Data Index: 311068 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 4.0817. Min Range: -4.0817

Max Act: 3.7735. Min Act: -0.0000

Data Index: 684019 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 4.0817. Min Range: -4.0817

Max Act: 4.0817. Min Act: -0.0000

Data Index: 726051 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 4.0817. Min Range: -4.0817

Max Act: 3.5498. Min Act: -0.0000

Data Index: 526281 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 4.0817. Min Range: -4.0817

Max Act: 3.2728. Min Act: -0.0000

Data Index: 720500 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 4.0817. Min Range: -4.0817

Max Act: 3.4901. Min Act: -0.0000

Data Index: 196535 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 4.0817. Min Range: -4.0817

Max Act: 3.1737. Min Act: -0.0000

Data Index: 185673 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.7123. Min Act: -0.0000

Data Index: 746604 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.6018. Min Act: -0.0000

Data Index: 1212015 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1237493 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.4400. Min Act: -0.0000

Data Index: 442307 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 4.0817. Min Range: -4.0817

Max Act: 3.0529. Min Act: -0.0000

Data Index: 141790 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.9027. Min Act: -0.0000

Data Index: 1222705 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.8678. Min Act: -0.0000

Data Index: 554720 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.7237. Min Act: -0.0000

Data Index: 1189605 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.7799. Min Act: -0.0000

Data Index: 1348524 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.6655. Min Act: -0.0000

Data Index: 819098 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.7919. Min Act: -0.0000

Data Index: 285311 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.7651. Min Act: -0.0000

Data Index: 742588 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 4.0817. Min Range: -4.0817

Max Act: 2.7688. Min Act: -0.0000

Data Index: 325442 (C4 (Web Text))

Max Activating Token Index: 629