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

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

Neuron 503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.1767. Min Act: -0.0000

Data Index: 438766 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.7873. Min Act: -0.0000

Data Index: 87187 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.0494. Min Act: -0.0000

Data Index: 857789 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.5050. Min Act: -0.0000

Data Index: 150000 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.5946. Min Act: -0.0001

Data Index: 84288 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.4120. Min Act: -0.0000

Data Index: 366032 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.6513. Min Act: -0.0000

Data Index: 138935 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.5720. Min Act: -0.0000

Data Index: 1233509 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.4577. Min Act: -0.0001

Data Index: 267375 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.5602. Min Act: -0.0000

Data Index: 1348514 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.3956. Min Act: -0.0000

Data Index: 1080746 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2693. Min Act: -0.0000

Data Index: 1036963 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.1309. Min Act: -0.0000

Data Index: 83419 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.3931. Min Act: -0.0000

Data Index: 976999 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.4509. Min Act: -0.0001

Data Index: 811532 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2058. Min Act: -0.0000

Data Index: 1019585 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2893. Min Act: -0.0000

Data Index: 1192090 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2752. Min Act: -0.0000

Data Index: 499326 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.4080. Min Act: -0.0000

Data Index: 1096049 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.1651. Min Act: -0.0000

Data Index: 344928 (C4 (Web Text))

Max Activating Token Index: 802