Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.9835. Min Act: -0.0000

Data Index: 956457 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 2.1857. Min Range: -2.1857

Max Act: 2.1857. Min Act: -0.0000

Data Index: 1280320 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.9557. Min Act: -0.0000

Data Index: 46052 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8727. Min Act: -0.0000

Data Index: 774858 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8452. Min Act: -0.0000

Data Index: 42409 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 2.1857. Min Range: -2.1857

Max Act: 2.0243. Min Act: -0.0000

Data Index: 66694 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8880. Min Act: -0.0000

Data Index: 791666 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.7880. Min Act: -0.0000

Data Index: 480200 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.7467. Min Act: -0.0000

Data Index: 41296 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.7625. Min Act: -0.0000

Data Index: 1099643 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8269. Min Act: -0.0000

Data Index: 1188911 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8231. Min Act: -0.0000

Data Index: 77167 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8073. Min Act: -0.0000

Data Index: 1327637 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8512. Min Act: -0.0000

Data Index: 684975 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.6637. Min Act: -0.0000

Data Index: 1023262 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8239. Min Act: -0.0000

Data Index: 10454 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.8596. Min Act: -0.0000

Data Index: 210970 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.7271. Min Act: -0.0000

Data Index: 687506 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.6040. Min Act: -0.0000

Data Index: 650042 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 2.1857. Min Range: -2.1857

Max Act: 1.5477. Min Act: -0.0000

Data Index: 996438 (C4 (Web Text))

Max Activating Token Index: 688