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

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

Neuron 5641 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6376. Min Act: -0.0001

Data Index: 518250 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6925. Min Act: -0.0001

Data Index: 712728 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6741. Min Act: -0.0001

Data Index: 538524 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6515. Min Act: -0.0001

Data Index: 462733 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6349. Min Act: -0.0001

Data Index: 176312 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6274. Min Act: -0.0000

Data Index: 580218 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5446. Min Act: -0.0001

Data Index: 1062145 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6035. Min Act: -0.0001

Data Index: 277266 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1195824 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6321. Min Act: -0.0001

Data Index: 1352171 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5625. Min Act: -0.0001

Data Index: 711630 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6574. Min Act: -0.0001

Data Index: 1270952 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6025. Min Act: -0.0000

Data Index: 182582 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5862. Min Act: -0.0001

Data Index: 409096 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1339288 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6122. Min Act: -0.0000

Data Index: 899687 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5588. Min Act: -0.0001

Data Index: 384798 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6537. Min Act: -0.0001

Data Index: 1226796 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5850. Min Act: -0.0001

Data Index: 945080 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6451. Min Act: -0.0000

Data Index: 822969 (C4 (Web Text))

Max Activating Token Index: 955