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

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

Neuron 4692 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.2086. Min Act: -0.0000

Data Index: 350526 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1747. Min Act: -0.0000

Data Index: 906181 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1617450 (Python Code)

Max Activating Token Index: 89

Text #3

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1471. Min Act: -0.0000

Data Index: 409431 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1331. Min Act: -0.0000

Data Index: 768004 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1403. Min Act: -0.0000

Data Index: 435438 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1303. Min Act: -0.0000

Data Index: 705530 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1126. Min Act: -0.0000

Data Index: 547265 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1093. Min Act: -0.0000

Data Index: 772049 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1113. Min Act: -0.0000

Data Index: 866983 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1144. Min Act: -0.0000

Data Index: 562774 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1095. Min Act: -0.0000

Data Index: 720253 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1011. Min Act: -0.0000

Data Index: 612133 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1063. Min Act: -0.0000

Data Index: 74288 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1096. Min Act: -0.0000

Data Index: 73744 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1425211 (Python Code)

Max Activating Token Index: 958

Text #16

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1514502 (Python Code)

Max Activating Token Index: 489

Text #17

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1158891 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1047507 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1047. Min Act: -0.0000

Data Index: 480870 (C4 (Web Text))

Max Activating Token Index: 936