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

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

Neuron 1008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0669. Min Range: -2.0669

Max Act: 2.0669. Min Act: -0.0000

Data Index: 535293 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5666. Min Act: -0.0000

Data Index: 1000170 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.6239. Min Act: -0.0000

Data Index: 1320424 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5163. Min Act: -0.0000

Data Index: 749251 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5064. Min Act: -0.0000

Data Index: 31982 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5113. Min Act: -0.0000

Data Index: 471231 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5096. Min Act: -0.0000

Data Index: 1190514 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1020101 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5762. Min Act: -0.0000

Data Index: 853646 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1336847 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1235460 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1010400 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1000860 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3803. Min Act: -0.0000

Data Index: 715544 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.4304. Min Act: -0.0000

Data Index: 202728 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3639. Min Act: -0.0000

Data Index: 154379 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1337756 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3429. Min Act: -0.0000

Data Index: 502511 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3307. Min Act: -0.0000

Data Index: 294617 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.3424. Min Act: -0.0000

Data Index: 11010 (C4 (Web Text))

Max Activating Token Index: 611