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

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

Neuron 1536 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: 0.8020. Min Range: -0.8020

Max Act: 0.8020. Min Act: -0.0001

Data Index: 818798 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7619. Min Act: -0.0001

Data Index: 919661 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7463. Min Act: -0.0001

Data Index: 74452 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1346973 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6809. Min Act: -0.0001

Data Index: 27798 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6947. Min Act: -0.0001

Data Index: 1118031 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6716. Min Act: -0.0001

Data Index: 750840 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6443. Min Act: -0.0001

Data Index: 1280073 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6791. Min Act: -0.0001

Data Index: 1282187 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6302. Min Act: -0.0001

Data Index: 819735 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6469. Min Act: -0.0001

Data Index: 676207 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6459. Min Act: -0.0001

Data Index: 1075271 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6351. Min Act: -0.0001

Data Index: 1085179 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1307125 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6363. Min Act: -0.0001

Data Index: 1141494 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6053. Min Act: -0.0001

Data Index: 1333776 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6287. Min Act: -0.0001

Data Index: 765712 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6259. Min Act: -0.0001

Data Index: 605922 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6066. Min Act: -0.0001

Data Index: 259147 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6429. Min Act: -0.0001

Data Index: 1064661 (C4 (Web Text))

Max Activating Token Index: 747