Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2622. Min Act: -0.0001

Data Index: 241667 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2378. Min Act: -0.0000

Data Index: 431528 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2199. Min Act: -0.0000

Data Index: 947467 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1332093 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1956. Min Act: 0.0000

Data Index: 237449 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1319404 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1072530 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1791. Min Act: -0.0001

Data Index: 342583 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1766. Min Act: -0.0000

Data Index: 271747 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1674. Min Act: -0.0000

Data Index: 99204 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1545. Min Act: -0.0000

Data Index: 341754 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1752. Min Act: 0.0000

Data Index: 675988 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1750. Min Act: -0.0000

Data Index: 610512 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1729. Min Act: -0.0000

Data Index: 208206 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1629. Min Act: -0.0000

Data Index: 25442 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1635. Min Act: -0.0001

Data Index: 530781 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1657. Min Act: -0.0000

Data Index: 781320 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1606. Min Act: -0.0000

Data Index: 246774 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1350214 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1551. Min Act: -0.0000

Data Index: 381107 (C4 (Web Text))

Max Activating Token Index: 541