Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2174 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1904. Min Act: -0.0000

Data Index: 613166 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1680. Min Act: -0.0000

Data Index: 765962 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1768. Min Act: -0.0000

Data Index: 503739 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1554. Min Act: -0.0000

Data Index: 75206 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1207911 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1131412 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1803. Min Act: -0.0000

Data Index: 254187 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1667. Min Act: -0.0001

Data Index: 655355 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1573. Min Act: -0.0000

Data Index: 738053 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1334318 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1642. Min Act: -0.0000

Data Index: 428706 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1459. Min Act: -0.0000

Data Index: 120304 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1561. Min Act: -0.0000

Data Index: 753521 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1231790 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1508. Min Act: -0.0000

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1415. Min Act: -0.0000

Data Index: 899772 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1290111 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1037389 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1400. Min Act: -0.0000

Data Index: 496009 (C4 (Web Text))

Max Activating Token Index: 811