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

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

Neuron 1576 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0672. Min Act: -0.0004

Data Index: 34076 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0467. Min Act: -0.0004

Data Index: 1095432 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0489. Min Act: -0.0004

Data Index: 1142717 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0449. Min Act: -0.0004

Data Index: 1356187 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0455. Min Act: -0.0004

Data Index: 557220 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0430. Min Act: -0.0004

Data Index: 720294 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0440. Min Act: -0.0004

Data Index: 1145059 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0424. Min Act: -0.0004

Data Index: 175798 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0414. Min Act: -0.0004

Data Index: 1237706 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0419. Min Act: -0.0004

Data Index: 327964 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0409. Min Act: -0.0004

Data Index: 372446 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0408. Min Act: -0.0004

Data Index: 839815 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0454. Min Act: -0.0004

Data Index: 11310 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0361. Min Act: -0.0004

Data Index: 762744 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0397. Min Act: -0.0004

Data Index: 487122 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0405. Min Act: -0.0004

Data Index: 636332 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0412. Min Act: -0.0004

Data Index: 387153 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0404. Min Act: -0.0004

Data Index: 496558 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0406. Min Act: -0.0004

Data Index: 1357176 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0421. Min Act: -0.0004

Data Index: 102598 (C4 (Web Text))

Max Activating Token Index: 5