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

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

Neuron 3756 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.4343. Min Act: -0.0001

Data Index: 877202 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.2269. Min Act: -0.0001

Data Index: 719608 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.2039. Min Act: -0.0001

Data Index: 1382393 (Python Code)

Max Activating Token Index: 496

Text #3

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1949. Min Act: -0.0001

Data Index: 1150715 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.2615. Min Act: -0.0001

Data Index: 317033 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.2353. Min Act: -0.0001

Data Index: 1057161 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1250. Min Act: -0.0001

Data Index: 1190823 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.0719. Min Act: -0.0001

Data Index: 105278 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1906. Min Act: -0.0001

Data Index: 90906 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1495. Min Act: -0.0001

Data Index: 1211781 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1765. Min Act: -0.0001

Data Index: 249532 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.0784. Min Act: -0.0001

Data Index: 815261 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.0769. Min Act: -0.0001

Data Index: 666058 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1322. Min Act: -0.0001

Data Index: 1182740 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1671. Min Act: -0.0001

Data Index: 397111 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1551. Min Act: -0.0001

Data Index: 615575 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1027. Min Act: -0.0001

Data Index: 943945 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.1703. Min Act: -0.0001

Data Index: 442973 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.4343. Min Range: -1.4343

Max Act: 0.9874. Min Act: -0.0001

Data Index: 69855 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.4343. Min Range: -1.4343

Max Act: 1.0975. Min Act: -0.0001

Data Index: 292901 (C4 (Web Text))

Max Activating Token Index: 391