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

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

Neuron 99 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: 1.1553. Min Range: -1.1553

Max Act: 1.1553. Min Act: -0.0001

Data Index: 1480429 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1369500 (Python Code)

Max Activating Token Index: 417

Text #2

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1597214 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1516039 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1327407 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.0219. Min Act: -0.0000

Data Index: 575130 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.0359. Min Act: -0.0000

Data Index: 168067 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9110. Min Act: -0.0000

Data Index: 494824 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.0571. Min Act: -0.0000

Data Index: 902674 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9399. Min Act: -0.0000

Data Index: 124115 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9540. Min Act: -0.0000

Data Index: 175899 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1230826 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9133. Min Act: -0.0000

Data Index: 443749 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9022. Min Act: -0.0000

Data Index: 286185 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9875. Min Act: -0.0000

Data Index: 902163 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9412. Min Act: -0.0000

Data Index: 978698 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1156885 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.8654. Min Act: -0.0000

Data Index: 326052 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9147. Min Act: -0.0000

Data Index: 450740 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.9170. Min Act: -0.0000

Data Index: 498828 (C4 (Web Text))

Max Activating Token Index: 288