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

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

Neuron 1016 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1243. Min Act: -0.0000

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0683. Min Act: -0.0000

Data Index: 778067 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0576. Min Act: -0.0000

Data Index: 158880 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0844. Min Act: -0.0000

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1158017 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1009. Min Act: -0.0000

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0194. Min Act: -0.0000

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0059. Min Act: -0.0000

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9687. Min Act: -0.0000

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9789. Min Act: -0.0000

Data Index: 205344 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9113. Min Act: -0.0000

Data Index: 549311 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9031. Min Act: -0.0000

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8876. Min Act: -0.0000

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8755. Min Act: -0.0000

Data Index: 736016 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8714. Min Act: -0.0000

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8671. Min Act: -0.0000

Data Index: 937956 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9210. Min Act: -0.0000

Data Index: 377130 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8940. Min Act: -0.0000

Data Index: 512525 (C4 (Web Text))

Max Activating Token Index: 274