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

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

Neuron 5098 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1733. Min Range: -2.1733

Max Act: 2.1239. Min Act: -0.0000

Data Index: 6917 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.1733. Min Range: -2.1733

Max Act: 2.1733. Min Act: -0.0000

Data Index: 1059901 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.9768. Min Act: -0.0000

Data Index: 240818 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.9408. Min Act: -0.0000

Data Index: 1074153 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.7708. Min Act: -0.0000

Data Index: 532662 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.7902. Min Act: -0.0000

Data Index: 900874 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.6841. Min Act: -0.0000

Data Index: 477694 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.8503. Min Act: -0.0000

Data Index: 97386 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.7434. Min Act: -0.0000

Data Index: 1271124 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.8144. Min Act: -0.0000

Data Index: 1043854 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.7154. Min Act: -0.0000

Data Index: 1013587 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.5351. Min Act: -0.0000

Data Index: 666546 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.6972. Min Act: -0.0000

Data Index: 391071 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.6057. Min Act: -0.0000

Data Index: 696995 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.5910. Min Act: -0.0000

Data Index: 1097693 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.5773. Min Act: -0.0000

Data Index: 200744 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.5400. Min Act: -0.0000

Data Index: 53419 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.5324. Min Act: -0.0000

Data Index: 1189187 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1268559 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 2.1733. Min Range: -2.1733

Max Act: 1.4346. Min Act: -0.0000

Data Index: 439331 (C4 (Web Text))

Max Activating Token Index: 245