Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5348 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2190. Min Range: -1.2190

Max Act: 1.2190. Min Act: 0.0001

Data Index: 365816 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.2190. Min Range: -1.2190

Max Act: 1.0967. Min Act: 0.0000

Data Index: 1295854 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.9733. Min Act: -0.0000

Data Index: 582823 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.2190. Min Range: -1.2190

Max Act: 1.0092. Min Act: -0.0000

Data Index: 873152 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.9408. Min Act: -0.0000

Data Index: 235837 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8559. Min Act: -0.0000

Data Index: 391816 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8404. Min Act: -0.0000

Data Index: 703431 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8723. Min Act: -0.0000

Data Index: 949766 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8190. Min Act: -0.0000

Data Index: 850439 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8420. Min Act: 0.0000

Data Index: 1193865 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8656. Min Act: -0.0000

Data Index: 181472 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8441. Min Act: -0.0000

Data Index: 159072 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1276018 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8658. Min Act: 0.0000

Data Index: 359670 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7071. Min Act: 0.0000

Data Index: 951559 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7777. Min Act: 0.0000

Data Index: 979354 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7795. Min Act: 0.0000

Data Index: 342889 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1081392 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7701. Min Act: -0.0000

Data Index: 674669 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7204. Min Act: -0.0000

Data Index: 637648 (C4 (Web Text))

Max Activating Token Index: 597