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

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

Neuron 4240 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0001

Data Index: 941561 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0545. Min Act: -0.0001

Data Index: 32080 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0495. Min Act: -0.0001

Data Index: 635646 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0516. Min Act: -0.0001

Data Index: 170288 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1262606 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1307926 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0587. Min Act: -0.0002

Data Index: 435728 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0604. Min Act: -0.0001

Data Index: 526762 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0513. Min Act: -0.0001

Data Index: 802372 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0488. Min Act: -0.0001

Data Index: 311251 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0541. Min Act: -0.0001

Data Index: 920248 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0511. Min Act: -0.0001

Data Index: 909576 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0465. Min Act: -0.0001

Data Index: 129027 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1202862 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0495. Min Act: -0.0001

Data Index: 87456 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0505. Min Act: -0.0001

Data Index: 625618 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0461. Min Act: -0.0001

Data Index: 342518 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0453. Min Act: -0.0001

Data Index: 89574 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0482. Min Act: -0.0001

Data Index: 91143 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0456. Min Act: -0.0001

Data Index: 668070 (C4 (Web Text))

Max Activating Token Index: 414