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

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

Neuron 3725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.3786. Min Act: -0.0000

Data Index: 946625 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1262764 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.3166. Min Act: -0.0000

Data Index: 868271 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.2243. Min Act: -0.0001

Data Index: 482537 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.1079. Min Act: -0.0001

Data Index: 130343 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.0780. Min Act: -0.0001

Data Index: 287221 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.0504. Min Act: -0.0001

Data Index: 222144 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.0764. Min Act: -0.0001

Data Index: 169411 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.0720. Min Act: -0.0001

Data Index: 932574 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.0414. Min Act: -0.0001

Data Index: 505730 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.3786. Min Range: -1.3786

Max Act: 1.0865. Min Act: -0.0001

Data Index: 1248372 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.9388. Min Act: -0.0001

Data Index: 237455 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.9791. Min Act: -0.0000

Data Index: 162672 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.9489. Min Act: -0.0001

Data Index: 1300617 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.9662. Min Act: -0.0001

Data Index: 426358 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.9017. Min Act: -0.0001

Data Index: 944840 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.9300. Min Act: -0.0001

Data Index: 753412 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1056320 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.8959. Min Act: -0.0000

Data Index: 847587 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.3786. Min Range: -1.3786

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1247823 (C4 (Web Text))

Max Activating Token Index: 122