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

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

Neuron 24 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.7940. Min Act: -0.0001

Data Index: 708885 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.7015. Min Act: -0.0001

Data Index: 616023 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.7096. Min Act: -0.0001

Data Index: 171696 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1142851 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.7393. Min Act: -0.0001

Data Index: 77328 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6780. Min Act: -0.0000

Data Index: 743564 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6638. Min Act: -0.0000

Data Index: 522326 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6325. Min Act: -0.0001

Data Index: 289738 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6301. Min Act: -0.0000

Data Index: 762102 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6176. Min Act: -0.0001

Data Index: 4852 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6000. Min Act: -0.0001

Data Index: 32148 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6682. Min Act: -0.0001

Data Index: 1324360 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6625. Min Act: -0.0000

Data Index: 698883 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6681. Min Act: -0.0000

Data Index: 69632 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6018. Min Act: -0.0001

Data Index: 128073 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6538. Min Act: -0.0001

Data Index: 889607 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6079. Min Act: -0.0001

Data Index: 111488 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6463. Min Act: -0.0001

Data Index: 308532 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6582. Min Act: -0.0000

Data Index: 688251 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6073. Min Act: -0.0001

Data Index: 830982 (C4 (Web Text))

Max Activating Token Index: 983