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

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

Neuron 3504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7758. Min Act: -0.0001

Data Index: 838639 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7481. Min Act: -0.0001

Data Index: 950742 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6866. Min Act: -0.0001

Data Index: 729801 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6852. Min Act: -0.0001

Data Index: 356677 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7060. Min Act: -0.0001

Data Index: 141829 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6947. Min Act: -0.0001

Data Index: 112398 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6913. Min Act: -0.0001

Data Index: 814365 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6832. Min Act: -0.0001

Data Index: 888920 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6861. Min Act: -0.0001

Data Index: 1225531 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6706. Min Act: -0.0001

Data Index: 1294397 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6564. Min Act: -0.0001

Data Index: 1247325 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6523. Min Act: -0.0001

Data Index: 16485 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6313. Min Act: -0.0001

Data Index: 246221 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6671. Min Act: -0.0001

Data Index: 313432 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6530. Min Act: -0.0001

Data Index: 460333 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1209584 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6359. Min Act: -0.0001

Data Index: 100796 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6650. Min Act: -0.0001

Data Index: 1044195 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6348. Min Act: -0.0001

Data Index: 607616 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6124. Min Act: -0.0001

Data Index: 502377 (C4 (Web Text))

Max Activating Token Index: 896