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

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

Neuron 2058 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.4411. Min Act: -0.0000

Data Index: 568095 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.4445. Min Act: -0.0000

Data Index: 220887 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.3799. Min Act: -0.0000

Data Index: 522647 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.4293. Min Act: -0.0000

Data Index: 206784 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.2690. Min Act: -0.0001

Data Index: 147409 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.3122. Min Act: -0.0001

Data Index: 726943 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.3065. Min Act: -0.0000

Data Index: 117947 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.3048. Min Act: -0.0000

Data Index: 671977 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.2132. Min Act: -0.0000

Data Index: 1235515 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.1429. Min Act: -0.0001

Data Index: 1080108 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.2513. Min Act: -0.0001

Data Index: 539090 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.1367. Min Act: -0.0000

Data Index: 593354 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.0800. Min Act: -0.0000

Data Index: 246845 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.1903. Min Act: -0.0000

Data Index: 985484 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.0539. Min Act: -0.0001

Data Index: 186891 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.1183. Min Act: -0.0001

Data Index: 527471 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9980. Min Act: -0.0000

Data Index: 893798 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9831. Min Act: -0.0001

Data Index: 913547 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.0632. Min Act: -0.0000

Data Index: 1063823 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9653. Min Act: -0.0000

Data Index: 564258 (C4 (Web Text))

Max Activating Token Index: 441