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

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

Neuron 19 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: 2.4962. Min Range: -2.4962

Max Act: 2.4962. Min Act: -0.0000

Data Index: 440386 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.2324. Min Act: -0.0000

Data Index: 516243 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.1580. Min Act: -0.0000

Data Index: 722422 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.1659. Min Act: -0.0000

Data Index: 686825 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.2571. Min Act: -0.0000

Data Index: 425169 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.1777. Min Act: -0.0000

Data Index: 142646 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.1646. Min Act: -0.0000

Data Index: 159250 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.0325. Min Act: -0.0000

Data Index: 337958 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.0361. Min Act: -0.0000

Data Index: 627337 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.8986. Min Act: -0.0000

Data Index: 809800 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 2.4962. Min Range: -2.4962

Max Act: 2.0702. Min Act: -0.0000

Data Index: 658752 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.8080. Min Act: -0.0000

Data Index: 774834 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.8104. Min Act: -0.0000

Data Index: 450059 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.6320. Min Act: -0.0000

Data Index: 110561 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.7879. Min Act: -0.0000

Data Index: 190045 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1501988 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.7674. Min Act: -0.0000

Data Index: 1135492 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.7607. Min Act: -0.0000

Data Index: 442641 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.7261. Min Act: -0.0000

Data Index: 503558 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 2.4962. Min Range: -2.4962

Max Act: 1.6278. Min Act: -0.0000

Data Index: 634638 (C4 (Web Text))

Max Activating Token Index: 652