Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1540 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.3401. Min Act: -0.0001

Data Index: 193560 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2834. Min Act: -0.0001

Data Index: 592223 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2684. Min Act: -0.0001

Data Index: 852282 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2604. Min Act: -0.0001

Data Index: 812164 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2397. Min Act: -0.0001

Data Index: 611604 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2355. Min Act: -0.0001

Data Index: 195761 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2558. Min Act: -0.0001

Data Index: 507316 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1215447 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2422. Min Act: -0.0001

Data Index: 514675 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2151. Min Act: -0.0001

Data Index: 254722 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2115. Min Act: -0.0001

Data Index: 94886 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2186. Min Act: -0.0001

Data Index: 623436 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2532. Min Act: -0.0001

Data Index: 254430 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2609. Min Act: -0.0001

Data Index: 107244 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2100. Min Act: -0.0001

Data Index: 1251636 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2173. Min Act: -0.0001

Data Index: 164668 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2199. Min Act: -0.0001

Data Index: 885518 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2012. Min Act: -0.0001

Data Index: 991101 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.1952. Min Act: -0.0001

Data Index: 646572 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.3401. Min Range: -0.3401

Max Act: 0.2128. Min Act: -0.0001

Data Index: 686524 (C4 (Web Text))

Max Activating Token Index: 481