Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2671. Min Act: -0.0000

Data Index: 884464 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2534. Min Act: -0.0000

Data Index: 456007 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2068. Min Act: -0.0000

Data Index: 331486 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1142408 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2018. Min Act: -0.0000

Data Index: 297212 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1235483 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1505. Min Act: -0.0001

Data Index: 342392 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2273. Min Act: -0.0000

Data Index: 852216 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1405. Min Act: -0.0001

Data Index: 809703 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1065. Min Act: -0.0000

Data Index: 593146 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1043. Min Act: -0.0000

Data Index: 476703 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1300174 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0687. Min Act: -0.0000

Data Index: 367896 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1256368 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9698. Min Act: -0.0000

Data Index: 437399 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9520. Min Act: -0.0001

Data Index: 850861 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.8865. Min Act: -0.0001

Data Index: 797521 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9785. Min Act: -0.0000

Data Index: 618050 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9433. Min Act: -0.0000

Data Index: 945283 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1238262 (C4 (Web Text))

Max Activating Token Index: 145