Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3401 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1080026 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0577. Min Act: -0.0001

Data Index: 258906 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0605. Min Act: -0.0001

Data Index: 841698 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0584. Min Act: -0.0001

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0572. Min Act: -0.0001

Data Index: 205786 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0555. Min Act: -0.0001

Data Index: 73547 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0530. Min Act: -0.0001

Data Index: 145374 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0558. Min Act: -0.0001

Data Index: 87667 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1167599 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0536. Min Act: -0.0001

Data Index: 6648 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0530. Min Act: -0.0001

Data Index: 367976 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0530. Min Act: -0.0001

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0499. Min Act: -0.0001

Data Index: 428188 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0551. Min Act: -0.0001

Data Index: 503180 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1282389 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1295454 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1212430 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0527. Min Act: -0.0001

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1169714 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0516. Min Act: -0.0001

Data Index: 388392 (C4 (Web Text))

Max Activating Token Index: 338