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

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

Neuron 4315 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5830. Min Act: -0.0001

Data Index: 240695 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5681. Min Act: -0.0001

Data Index: 657170 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5312. Min Act: -0.0001

Data Index: 363454 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4887. Min Act: -0.0001

Data Index: 834629 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1239597 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4462. Min Act: -0.0001

Data Index: 660481 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4593. Min Act: -0.0001

Data Index: 871716 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1292350 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5050. Min Act: -0.0001

Data Index: 333676 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4416. Min Act: -0.0001

Data Index: 858963 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4750. Min Act: -0.0001

Data Index: 622364 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4519. Min Act: -0.0001

Data Index: 581410 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4688. Min Act: -0.0000

Data Index: 973794 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4604. Min Act: -0.0001

Data Index: 713447 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4353. Min Act: -0.0001

Data Index: 1010774 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4405. Min Act: -0.0001

Data Index: 149322 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4261. Min Act: -0.0001

Data Index: 468464 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4412. Min Act: -0.0001

Data Index: 747784 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4237. Min Act: -0.0001

Data Index: 386528 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3670. Min Act: -0.0001

Data Index: 675620 (C4 (Web Text))

Max Activating Token Index: 166