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

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

Neuron 3399 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.8289. Min Act: -0.0001

Data Index: 532505 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.7294. Min Act: -0.0001

Data Index: 601719 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5981. Min Act: -0.0001

Data Index: 517963 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6008. Min Act: -0.0001

Data Index: 332305 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5341. Min Act: -0.0001

Data Index: 515816 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5747. Min Act: -0.0001

Data Index: 378125 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5364. Min Act: -0.0001

Data Index: 767106 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1001564 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4928. Min Act: -0.0001

Data Index: 740688 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5119. Min Act: -0.0001

Data Index: 257596 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4763. Min Act: -0.0001

Data Index: 555192 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4806. Min Act: -0.0001

Data Index: 475551 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4710. Min Act: -0.0001

Data Index: 482458 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4754. Min Act: -0.0001

Data Index: 1277301 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4382. Min Act: -0.0001

Data Index: 784401 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4674. Min Act: -0.0001

Data Index: 665355 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4519. Min Act: -0.0001

Data Index: 755593 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4597. Min Act: -0.0001

Data Index: 242696 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4925. Min Act: -0.0001

Data Index: 252942 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.4746. Min Act: -0.0001

Data Index: 200951 (C4 (Web Text))

Max Activating Token Index: 738