Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2136 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4954. Min Act: -0.0000

Data Index: 386468 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4886. Min Act: -0.0001

Data Index: 472857 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4278. Min Act: -0.0001

Data Index: 1029389 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4225. Min Act: -0.0001

Data Index: 1282507 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4063. Min Act: -0.0000

Data Index: 93742 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3988. Min Act: -0.0001

Data Index: 937274 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4009. Min Act: -0.0001

Data Index: 925391 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3860. Min Act: 0.0001

Data Index: 940669 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3804. Min Act: -0.0000

Data Index: 609183 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3772. Min Act: -0.0001

Data Index: 1265835 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3766. Min Act: -0.0001

Data Index: 500319 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3771. Min Act: -0.0000

Data Index: 314691 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3823. Min Act: -0.0001

Data Index: 881785 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3784. Min Act: -0.0001

Data Index: 675127 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3751. Min Act: -0.0001

Data Index: 774345 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3561. Min Act: -0.0001

Data Index: 250528 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3358. Min Act: -0.0000

Data Index: 721004 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3515. Min Act: -0.0001

Data Index: 58409 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1216786 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3454. Min Act: -0.0001

Data Index: 818174 (C4 (Web Text))

Max Activating Token Index: 98