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

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

Neuron 3840 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2853. Min Act: -0.0001

Data Index: 626762 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2820. Min Act: -0.0001

Data Index: 9833 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2551. Min Act: -0.0001

Data Index: 730018 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2642. Min Act: -0.0001

Data Index: 968637 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2491. Min Act: -0.0001

Data Index: 296160 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1109680 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2393. Min Act: -0.0001

Data Index: 812067 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1267805 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2352. Min Act: -0.0001

Data Index: 70743 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2066. Min Act: -0.0001

Data Index: 821905 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2222. Min Act: -0.0001

Data Index: 632062 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1343618 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2289. Min Act: -0.0001

Data Index: 434339 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2256. Min Act: -0.0001

Data Index: 985378 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2119. Min Act: -0.0001

Data Index: 596259 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2240. Min Act: -0.0001

Data Index: 611033 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2109. Min Act: -0.0001

Data Index: 214596 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.1983. Min Act: -0.0001

Data Index: 362081 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2201. Min Act: -0.0001

Data Index: 460414 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1117608 (C4 (Web Text))

Max Activating Token Index: 301