Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 573 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1290. Min Range: -2.1290

Max Act: 2.1290. Min Act: -0.0000

Data Index: 855890 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 2.1290. Min Range: -2.1290

Max Act: 1.9809. Min Act: -0.0000

Data Index: 155142 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 2.1290. Min Range: -2.1290

Max Act: 1.6960. Min Act: -0.0000

Data Index: 98964 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 2.1290. Min Range: -2.1290

Max Act: 1.6962. Min Act: -0.0000

Data Index: 276279 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 2.1290. Min Range: -2.1290

Max Act: 1.4812. Min Act: -0.0000

Data Index: 299928 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 2.1290. Min Range: -2.1290

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1251567 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1186023 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1342707 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.7765. Min Act: -0.0000

Data Index: 897694 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1344105 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1010216 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6857. Min Act: -0.0000

Data Index: 487212 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6722. Min Act: -0.0000

Data Index: 866881 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1334392 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6473. Min Act: -0.0000

Data Index: 35065 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1131549 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6236. Min Act: -0.0000

Data Index: 437358 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6178. Min Act: -0.0000

Data Index: 426404 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.6140. Min Act: -0.0000

Data Index: 410459 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 2.1290. Min Range: -2.1290

Max Act: 0.5716. Min Act: -0.0000

Data Index: 888663 (C4 (Web Text))

Max Activating Token Index: 320