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

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

Neuron 748 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7705. Min Act: -0.0003

Data Index: 87131 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6826. Min Act: -0.0003

Data Index: 751439 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6790. Min Act: -0.0003

Data Index: 1252562 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5472. Min Act: -0.0003

Data Index: 467137 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5345. Min Act: -0.0003

Data Index: 373156 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5129. Min Act: -0.0003

Data Index: 536175 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4254. Min Act: -0.0003

Data Index: 614886 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4667. Min Act: -0.0003

Data Index: 1027855 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4846. Min Act: -0.0003

Data Index: 1038240 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4676. Min Act: -0.0003

Data Index: 1063469 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4968. Min Act: -0.0003

Data Index: 1127882 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4738. Min Act: -0.0003

Data Index: 816320 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4667. Min Act: -0.0003

Data Index: 1264273 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4443. Min Act: -0.0003

Data Index: 796611 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4570. Min Act: -0.0003

Data Index: 1081431 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4375. Min Act: -0.0003

Data Index: 337645 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4120. Min Act: -0.0003

Data Index: 469000 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4234. Min Act: -0.0003

Data Index: 214975 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4247. Min Act: -0.0003

Data Index: 989690 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.4351. Min Act: -0.0003

Data Index: 958761 (C4 (Web Text))

Max Activating Token Index: 672