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

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

Neuron 1750 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: 0.1799. Min Range: -0.1799

Max Act: 0.1799. Min Act: -0.0000

Data Index: 12375 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1796. Min Act: -0.0000

Data Index: 350683 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1529. Min Act: -0.0000

Data Index: 581292 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1380. Min Act: -0.0000

Data Index: 560100 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1146844 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1387. Min Act: -0.0000

Data Index: 223575 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1374. Min Act: -0.0000

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1268. Min Act: -0.0001

Data Index: 391049 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1290935 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1151611 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1229. Min Act: -0.0001

Data Index: 290545 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1188712 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1188. Min Act: -0.0000

Data Index: 61989 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1354873 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1115. Min Act: -0.0001

Data Index: 261965 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1077. Min Act: -0.0001

Data Index: 921990 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1211457 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1185260 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1021147 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1033. Min Act: -0.0000

Data Index: 143681 (C4 (Web Text))

Max Activating Token Index: 879