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

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

Neuron 2541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0000

Data Index: 572698 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1433029 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1602363 (Python Code)

Max Activating Token Index: 463

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1652307 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1525988 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0581. Min Act: -0.0000

Data Index: 158390 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1508286 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1555237 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1529358 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1412076 (Python Code)

Max Activating Token Index: 620

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1501085 (Python Code)

Max Activating Token Index: 835

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1427513 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1432020 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0583. Min Act: -0.0000

Data Index: 1573664 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1510232 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1428963 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1375244 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1469394 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0521. Min Act: -0.0000

Data Index: 739481 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1627713 (Python Code)

Max Activating Token Index: 311