Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2660 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2252. Min Act: -0.0001

Data Index: 1017949 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2167. Min Act: -0.0001

Data Index: 264197 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2237. Min Act: -0.0001

Data Index: 666774 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2185. Min Act: -0.0001

Data Index: 677591 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2065. Min Act: -0.0001

Data Index: 486543 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1192420 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1922. Min Act: -0.0001

Data Index: 928883 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1119207 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1317934 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1259504 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1973. Min Act: -0.0001

Data Index: 971895 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2110. Min Act: -0.0001

Data Index: 678811 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1314969 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1906. Min Act: -0.0001

Data Index: 939501 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1822. Min Act: -0.0001

Data Index: 993293 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1790. Min Act: -0.0001

Data Index: 87867 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1897. Min Act: -0.0001

Data Index: 1080014 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1780. Min Act: -0.0001

Data Index: 93286 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1772. Min Act: -0.0001

Data Index: 360099 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1019330 (C4 (Web Text))

Max Activating Token Index: 92