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

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

Neuron 713 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1315180 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.5756. Min Act: -0.0001

Data Index: 671277 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1292. Min Act: -0.0001

Data Index: 1351707 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0615. Min Act: -0.0001

Data Index: 105461 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1808. Min Act: -0.0001

Data Index: 246696 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0842. Min Act: -0.0001

Data Index: 245509 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1471819 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0497. Min Act: -0.0001

Data Index: 1476290 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9636. Min Act: -0.0001

Data Index: 1315563 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9227. Min Act: -0.0001

Data Index: 745070 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1616213 (Python Code)

Max Activating Token Index: 424

Text #11

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8995. Min Act: -0.0001

Data Index: 867109 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8912. Min Act: -0.0001

Data Index: 1053077 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0022. Min Act: -0.0001

Data Index: 1113720 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8675. Min Act: -0.0001

Data Index: 1334181 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.7961. Min Act: -0.0001

Data Index: 309394 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8763. Min Act: -0.0001

Data Index: 279632 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8783. Min Act: -0.0001

Data Index: 602097 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8730. Min Act: -0.0001

Data Index: 67428 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8104. Min Act: -0.0001

Data Index: 167140 (C4 (Web Text))

Max Activating Token Index: 952