Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 58 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0562. Min Act: -0.0001

Data Index: 913341 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0564. Min Act: -0.0001

Data Index: 724174 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0548. Min Act: -0.0001

Data Index: 703709 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0520. Min Act: -0.0001

Data Index: 179327 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0526. Min Act: -0.0001

Data Index: 815113 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0515. Min Act: -0.0001

Data Index: 146765 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1294676 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0507. Min Act: -0.0001

Data Index: 649192 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0530. Min Act: -0.0001

Data Index: 954174 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0513. Min Act: -0.0001

Data Index: 111633 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0524. Min Act: -0.0001

Data Index: 170819 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0499. Min Act: -0.0001

Data Index: 303153 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1314407 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0497. Min Act: -0.0001

Data Index: 731861 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0501. Min Act: -0.0001

Data Index: 84523 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0515. Min Act: -0.0001

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1051611 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0509. Min Act: -0.0001

Data Index: 202089 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1007971 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0491. Min Act: -0.0001

Data Index: 59702 (C4 (Web Text))

Max Activating Token Index: 835