Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 45 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.1611. Min Act: -0.0001

Data Index: 408619 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0134. Min Act: -0.0001

Data Index: 1056463 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9372. Min Act: -0.0001

Data Index: 1322307 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9025. Min Act: -0.0001

Data Index: 120465 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8942. Min Act: -0.0001

Data Index: 898612 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9113. Min Act: -0.0001

Data Index: 603827 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1149780 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8737. Min Act: -0.0001

Data Index: 440744 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1343186 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8430. Min Act: -0.0001

Data Index: 1136973 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8169. Min Act: -0.0000

Data Index: 490974 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8074. Min Act: -0.0001

Data Index: 1282041 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8248. Min Act: -0.0000

Data Index: 209360 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8031. Min Act: -0.0000

Data Index: 521764 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8183. Min Act: -0.0001

Data Index: 1317908 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1062571 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.7676. Min Act: -0.0001

Data Index: 386827 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8069. Min Act: -0.0001

Data Index: 1250231 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.7745. Min Act: -0.0001

Data Index: 106288 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.7749. Min Act: -0.0001

Data Index: 43179 (C4 (Web Text))

Max Activating Token Index: 52