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

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

Neuron 2437 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: 2.5647. Min Range: -2.5647

Max Act: 2.4496. Min Act: -0.0000

Data Index: 402217 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.4014. Min Act: -0.0000

Data Index: 835510 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.5647. Min Act: -0.0000

Data Index: 1133230 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.4496. Min Act: -0.0000

Data Index: 843645 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.8024. Min Act: -0.0000

Data Index: 525828 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1112. Min Act: -0.0000

Data Index: 248545 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9748. Min Act: -0.0000

Data Index: 574838 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.0578. Min Act: -0.0000

Data Index: 482054 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1497. Min Act: -0.0000

Data Index: 963532 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.8203. Min Act: -0.0000

Data Index: 416271 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1168. Min Act: -0.0000

Data Index: 241590 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9893. Min Act: -0.0000

Data Index: 1210360 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.8698. Min Act: -0.0000

Data Index: 493475 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9349. Min Act: -0.0000

Data Index: 444790 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.7389. Min Act: -0.0000

Data Index: 731073 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1116. Min Act: -0.0000

Data Index: 108710 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.0010. Min Act: -0.0000

Data Index: 499150 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1079. Min Act: -0.0000

Data Index: 422820 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.7108. Min Act: -0.0000

Data Index: 13837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9707. Min Act: -0.0000

Data Index: 921922 (C4 (Web Text))

Max Activating Token Index: 354