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

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

Neuron 288 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1198736 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.3357. Min Act: -0.0000

Data Index: 834931 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.1763. Min Act: -0.0000

Data Index: 506596 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.2936. Min Act: -0.0000

Data Index: 467155 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.2494. Min Act: -0.0000

Data Index: 225287 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.2354. Min Act: -0.0000

Data Index: 1240235 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.2190. Min Act: -0.0000

Data Index: 212904 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.1904. Min Act: -0.0000

Data Index: 682080 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1038078 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.1317. Min Act: -0.0000

Data Index: 931990 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0947. Min Act: -0.0000

Data Index: 724653 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1115853 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0757. Min Act: -0.0000

Data Index: 956745 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1337411 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0978. Min Act: -0.0000

Data Index: 146447 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0646. Min Act: -0.0000

Data Index: 624328 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0639. Min Act: -0.0000

Data Index: 868718 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0518. Min Act: -0.0000

Data Index: 1019658 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1042824 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.0468. Min Act: -0.0000

Data Index: 194149 (C4 (Web Text))

Max Activating Token Index: 835