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

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

Neuron 3896 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.2180. Min Act: -0.0000

Data Index: 302811 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.1802. Min Act: 0.0000

Data Index: 73656 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1063360 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.1614. Min Act: -0.0000

Data Index: 521603 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.1547. Min Act: -0.0000

Data Index: 167628 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.0912. Min Act: 0.0000

Data Index: 56665 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.0726. Min Act: -0.0000

Data Index: 857453 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.0387. Min Act: -0.0000

Data Index: 65400 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.1300. Min Act: -0.0000

Data Index: 480541 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.0132. Min Act: 0.0000

Data Index: 577481 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.0685. Min Act: -0.0000

Data Index: 814541 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1001559 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.2180. Min Range: -1.2180

Max Act: 0.9837. Min Act: -0.0000

Data Index: 624466 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 1.2180. Min Range: -1.2180

Max Act: 1.0377. Min Act: -0.0000

Data Index: 256715 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.2180. Min Range: -1.2180

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1059838 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.2180. Min Range: -1.2180

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1175968 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.2180. Min Range: -1.2180

Max Act: 0.9561. Min Act: -0.0000

Data Index: 279181 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.2180. Min Range: -1.2180

Max Act: 0.8845. Min Act: -0.0000

Data Index: 1191513 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 1.2180. Min Range: -1.2180

Max Act: 0.8750. Min Act: -0.0000

Data Index: 278535 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.2180. Min Range: -1.2180

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1087393 (C4 (Web Text))

Max Activating Token Index: 906