Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1927 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1990. Min Act: -0.0000

Data Index: 297537 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1499. Min Act: -0.0000

Data Index: 222971 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1418. Min Act: -0.0000

Data Index: 69267 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1270. Min Act: -0.0000

Data Index: 296868 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1207. Min Act: -0.0000

Data Index: 801036 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1295. Min Act: -0.0000

Data Index: 686160 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1204. Min Act: -0.0000

Data Index: 828487 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1201. Min Act: -0.0000

Data Index: 56005 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1106. Min Act: -0.0000

Data Index: 596268 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1102. Min Act: -0.0000

Data Index: 133603 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1092. Min Act: -0.0000

Data Index: 849544 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.0916. Min Act: -0.0000

Data Index: 183508 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1332021 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1005. Min Act: -0.0000

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1225247 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1132764 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1051. Min Act: -0.0000

Data Index: 317434 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1057529 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.0968. Min Act: -0.0000

Data Index: 649999 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.0960. Min Act: -0.0000

Data Index: 431908 (C4 (Web Text))

Max Activating Token Index: 122