Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0604. Min Act: -0.0002

Data Index: 118124 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0637. Min Act: -0.0002

Data Index: 26284 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0647. Min Act: -0.0002

Data Index: 51100 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0593. Min Act: -0.0002

Data Index: 179949 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0629. Min Act: -0.0002

Data Index: 753829 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0565. Min Act: -0.0002

Data Index: 605514 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0607. Min Act: -0.0002

Data Index: 400052 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0592. Min Act: -0.0002

Data Index: 388939 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0621. Min Act: -0.0002

Data Index: 553431 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0596. Min Act: -0.0002

Data Index: 532910 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1008455 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1258455 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1504716 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0526. Min Act: -0.0002

Data Index: 459558 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0549. Min Act: -0.0002

Data Index: 395353 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0586. Min Act: -0.0002

Data Index: 664835 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1265193 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0500. Min Act: -0.0002

Data Index: 499408 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0582. Min Act: -0.0002

Data Index: 717984 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0545. Min Act: -0.0002

Data Index: 803956 (C4 (Web Text))

Max Activating Token Index: 336