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

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

Neuron 842 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3991. Min Act: 0.0001

Data Index: 704017 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3801. Min Act: 0.0000

Data Index: 783205 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3565. Min Act: 0.0001

Data Index: 1097645 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3497. Min Act: -0.0000

Data Index: 18957 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3576. Min Act: 0.0000

Data Index: 1160630 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1616886 (Python Code)

Max Activating Token Index: 884

Text #6

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1318199 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3043. Min Act: 0.0000

Data Index: 152859 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2934. Min Act: 0.0000

Data Index: 122160 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1443371 (Python Code)

Max Activating Token Index: 776

Text #10

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2814. Min Act: 0.0000

Data Index: 1340607 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2755. Min Act: 0.0000

Data Index: 40075 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1024373 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2741. Min Act: 0.0000

Data Index: 473825 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2645. Min Act: -0.0000

Data Index: 748967 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2685. Min Act: -0.0000

Data Index: 379169 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2564. Min Act: 0.0001

Data Index: 196488 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1426900 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1354007 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2628. Min Act: -0.0000

Data Index: 239857 (C4 (Web Text))

Max Activating Token Index: 642