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

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

Neuron 3076 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1661. Min Act: -0.0002

Data Index: 1083422 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1668. Min Act: -0.0002

Data Index: 1246272 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0001

Data Index: 425187 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0001

Data Index: 1273724 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1553. Min Act: -0.0002

Data Index: 1070095 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1532. Min Act: -0.0001

Data Index: 454720 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1521. Min Act: -0.0001

Data Index: 93647 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1531. Min Act: -0.0001

Data Index: 785222 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1319187 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1364. Min Act: -0.0002

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1414. Min Act: -0.0002

Data Index: 1158955 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1368. Min Act: -0.0002

Data Index: 545891 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1456. Min Act: -0.0001

Data Index: 525043 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1350. Min Act: -0.0002

Data Index: 550900 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1492. Min Act: -0.0002

Data Index: 864063 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1377. Min Act: -0.0001

Data Index: 228531 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1313. Min Act: -0.0002

Data Index: 816440 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1436. Min Act: -0.0002

Data Index: 564836 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1374. Min Act: -0.0001

Data Index: 700874 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1469. Min Act: -0.0001

Data Index: 670171 (C4 (Web Text))

Max Activating Token Index: 81