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

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

Neuron 3136 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1836. Min Act: -0.0000

Data Index: 655646 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1680. Min Act: -0.0000

Data Index: 431332 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1670. Min Act: -0.0000

Data Index: 326551 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1729. Min Act: -0.0001

Data Index: 1306523 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1456. Min Act: -0.0001

Data Index: 80940 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1459. Min Act: -0.0000

Data Index: 580386 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1489. Min Act: -0.0000

Data Index: 812295 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1430. Min Act: -0.0001

Data Index: 161738 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1344. Min Act: -0.0001

Data Index: 68667 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1120991 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1170203 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1419. Min Act: -0.0001

Data Index: 662600 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1451. Min Act: -0.0001

Data Index: 522019 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1392. Min Act: -0.0000

Data Index: 243359 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1238. Min Act: -0.0001

Data Index: 214371 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1312. Min Act: -0.0001

Data Index: 12319 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1259. Min Act: -0.0001

Data Index: 552086 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1059390 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1052875 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1336. Min Act: -0.0001

Data Index: 483576 (C4 (Web Text))

Max Activating Token Index: 408