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

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

Neuron 4726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4351. Min Range: -2.4351

Max Act: 2.2833. Min Act: -0.0000

Data Index: 1633754 (Python Code)

Max Activating Token Index: 103

Text #1

Max Range: 2.4351. Min Range: -2.4351

Max Act: 2.4351. Min Act: -0.0000

Data Index: 1578021 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.9880. Min Act: -0.0000

Data Index: 1373339 (Python Code)

Max Activating Token Index: 828

Text #3

Max Range: 2.4351. Min Range: -2.4351

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1601205 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.9608. Min Act: -0.0000

Data Index: 1585484 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1434511 (Python Code)

Max Activating Token Index: 215

Text #6

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.9352. Min Act: -0.0000

Data Index: 326119 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.9158. Min Act: -0.0000

Data Index: 1550643 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.9255. Min Act: -0.0000

Data Index: 563342 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.9884. Min Act: -0.0000

Data Index: 1432276 (Python Code)

Max Activating Token Index: 797

Text #10

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1142099 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.9283. Min Act: -0.0000

Data Index: 1372553 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1074690 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.8835. Min Act: -0.0001

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.6804. Min Act: -0.0000

Data Index: 918713 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1407513 (Python Code)

Max Activating Token Index: 975

Text #16

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1559493 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.7377. Min Act: -0.0000

Data Index: 13075 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.6737. Min Act: -0.0001

Data Index: 1606650 (Python Code)

Max Activating Token Index: 943

Text #19

Max Range: 2.4351. Min Range: -2.4351

Max Act: 1.7128. Min Act: -0.0000

Data Index: 89484 (C4 (Web Text))

Max Activating Token Index: 337