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

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

Neuron 2989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1042453 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1300. Min Act: -0.0000

Data Index: 820147 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1618112 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1091. Min Act: -0.0001

Data Index: 5243 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1119. Min Act: -0.0001

Data Index: 476485 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1184158 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1302531 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1377278 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.0988. Min Act: -0.0001

Data Index: 116535 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1419609 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1096. Min Act: -0.0000

Data Index: 597381 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1108202 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1051. Min Act: -0.0000

Data Index: 844270 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1010. Min Act: -0.0000

Data Index: 254617 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1090. Min Act: -0.0000

Data Index: 988974 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1072. Min Act: -0.0001

Data Index: 157525 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1379448 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1002. Min Act: -0.0000

Data Index: 125706 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1028. Min Act: -0.0001

Data Index: 800136 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1579611 (Python Code)

Max Activating Token Index: 627