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

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

Neuron 421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0886. Min Act: -0.0001

Data Index: 525075 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0289. Min Act: -0.0001

Data Index: 1298595 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0055. Min Act: -0.0001

Data Index: 923963 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9876. Min Act: -0.0001

Data Index: 1260521 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0020. Min Act: -0.0001

Data Index: 187480 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9452. Min Act: -0.0001

Data Index: 1244051 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9124. Min Act: -0.0001

Data Index: 1152317 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8740. Min Act: -0.0001

Data Index: 1310745 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8971. Min Act: -0.0001

Data Index: 473233 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8604. Min Act: -0.0001

Data Index: 517356 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8061. Min Act: -0.0001

Data Index: 859935 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8762. Min Act: -0.0001

Data Index: 1038350 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8681. Min Act: -0.0001

Data Index: 288160 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8504. Min Act: -0.0001

Data Index: 1415515 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8382. Min Act: -0.0001

Data Index: 565306 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8393. Min Act: -0.0001

Data Index: 669429 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.7515. Min Act: -0.0001

Data Index: 801451 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8522. Min Act: -0.0001

Data Index: 403891 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8379. Min Act: -0.0001

Data Index: 277209 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.7740. Min Act: -0.0001

Data Index: 1146944 (C4 (Web Text))

Max Activating Token Index: 825