Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1086 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1337982 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5986. Min Act: -0.0000

Data Index: 194189 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5371. Min Act: -0.0000

Data Index: 925422 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1138371 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4929. Min Act: -0.0000

Data Index: 549174 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4873. Min Act: -0.0000

Data Index: 861291 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4822. Min Act: -0.0000

Data Index: 150456 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4745. Min Act: -0.0000

Data Index: 648833 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3965. Min Act: -0.0000

Data Index: 912290 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4448. Min Act: -0.0000

Data Index: 651783 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4565. Min Act: -0.0000

Data Index: 640701 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1170753 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4334. Min Act: -0.0000

Data Index: 71060 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4482. Min Act: -0.0000

Data Index: 530021 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4298. Min Act: -0.0000

Data Index: 324684 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4407. Min Act: -0.0000

Data Index: 708906 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4395. Min Act: -0.0000

Data Index: 911208 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3712. Min Act: -0.0000

Data Index: 778843 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1058672 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3868. Min Act: -0.0000

Data Index: 898845 (C4 (Web Text))

Max Activating Token Index: 807