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

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

Neuron 204 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1099482 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1001628 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0642. Min Act: -0.0002

Data Index: 91760 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0570. Min Act: -0.0002

Data Index: 432510 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0612. Min Act: -0.0002

Data Index: 117625 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0535. Min Act: -0.0002

Data Index: 323976 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0546. Min Act: -0.0002

Data Index: 283341 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0533. Min Act: -0.0002

Data Index: 672316 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0542. Min Act: -0.0002

Data Index: 785623 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1543652 (Python Code)

Max Activating Token Index: 167

Text #10

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0536. Min Act: -0.0002

Data Index: 620536 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1213180 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0531. Min Act: -0.0002

Data Index: 617277 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0508. Min Act: -0.0002

Data Index: 91602 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1029984 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1281644 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0564. Min Act: -0.0002

Data Index: 221625 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0525. Min Act: -0.0002

Data Index: 46915 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1242562 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1515068 (Python Code)

Max Activating Token Index: 841