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

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

Neuron 4072 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1407532 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1329. Min Act: -0.0001

Data Index: 338139 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1643156 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1322. Min Act: -0.0002

Data Index: 316220 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1528574 (Python Code)

Max Activating Token Index: 871

Text #5

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1452571 (Python Code)

Max Activating Token Index: 527

Text #6

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1105. Min Act: -0.0002

Data Index: 151478 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1109957 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1628232 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1286500 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1168. Min Act: -0.0002

Data Index: 566793 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1093. Min Act: -0.0001

Data Index: 388038 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1064. Min Act: -0.0002

Data Index: 692820 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1065. Min Act: -0.0002

Data Index: 827276 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1274023 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1002. Min Act: -0.0002

Data Index: 362466 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0991. Min Act: -0.0002

Data Index: 23777 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0991. Min Act: -0.0001

Data Index: 511946 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1014. Min Act: -0.0001

Data Index: 480196 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1039. Min Act: -0.0002

Data Index: 96880 (C4 (Web Text))

Max Activating Token Index: 868