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

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

Neuron 863 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: 0.4573. Min Range: -0.4573

Max Act: 0.4573. Min Act: -0.0000

Data Index: 552874 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4564. Min Act: -0.0001

Data Index: 601411 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4030. Min Act: -0.0000

Data Index: 300893 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1039691 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4078. Min Act: -0.0000

Data Index: 377038 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3551. Min Act: -0.0001

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3826. Min Act: -0.0001

Data Index: 33350 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3713. Min Act: -0.0001

Data Index: 299989 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3698. Min Act: -0.0001

Data Index: 404792 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3378. Min Act: -0.0000

Data Index: 204803 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1082715 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1005595 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3376. Min Act: -0.0001

Data Index: 1096358 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3469. Min Act: -0.0000

Data Index: 359685 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3545. Min Act: -0.0000

Data Index: 795321 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3133. Min Act: -0.0000

Data Index: 936698 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1123332 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1171691 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1195165 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2862. Min Act: -0.0001

Data Index: 342553 (C4 (Web Text))

Max Activating Token Index: 964