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

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

Neuron 1172 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1173131 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1625. Min Act: -0.0001

Data Index: 245722 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1483. Min Act: -0.0001

Data Index: 209216 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1293. Min Act: -0.0001

Data Index: 313399 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1438. Min Act: -0.0001

Data Index: 137844 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1516. Min Act: -0.0001

Data Index: 529905 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1222. Min Act: -0.0001

Data Index: 751810 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1600399 (Python Code)

Max Activating Token Index: 817

Text #8

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1195. Min Act: -0.0001

Data Index: 631064 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1018. Min Act: -0.0001

Data Index: 944195 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1047. Min Act: -0.0001

Data Index: 291243 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1036. Min Act: -0.0001

Data Index: 830409 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.0988. Min Act: -0.0001

Data Index: 644627 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1237309 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1486804 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1468810 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.0965. Min Act: -0.0001

Data Index: 69574 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1498349 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.0936. Min Act: -0.0001

Data Index: 714474 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1407337 (Python Code)

Max Activating Token Index: 493