Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4514 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1788. Min Range: -1.1788

Max Act: 1.1788. Min Act: -0.0001

Data Index: 714372 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.1788. Min Range: -1.1788

Max Act: 1.1495. Min Act: -0.0000

Data Index: 8065 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 1.1788. Min Range: -1.1788

Max Act: 1.0033. Min Act: -0.0000

Data Index: 894343 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.9515. Min Act: -0.0001

Data Index: 143986 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.8843. Min Act: -0.0001

Data Index: 1293557 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6692. Min Act: -0.0001

Data Index: 816021 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.8965. Min Act: -0.0001

Data Index: 46915 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.8150. Min Act: -0.0001

Data Index: 428506 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.7437. Min Act: -0.0000

Data Index: 706643 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.7357. Min Act: -0.0001

Data Index: 734338 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6522. Min Act: -0.0001

Data Index: 986300 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6672. Min Act: -0.0001

Data Index: 535917 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.7227. Min Act: -0.0001

Data Index: 644294 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6962. Min Act: -0.0001

Data Index: 647234 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.7054. Min Act: -0.0001

Data Index: 1034053 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6904. Min Act: -0.0001

Data Index: 607075 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.5973. Min Act: -0.0001

Data Index: 180942 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6136. Min Act: -0.0001

Data Index: 1329224 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6568. Min Act: -0.0001

Data Index: 494154 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.1788. Min Range: -1.1788

Max Act: 0.6305. Min Act: -0.0001

Data Index: 905962 (C4 (Web Text))

Max Activating Token Index: 14