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

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

Neuron 819 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.5148. Min Act: -0.0000

Data Index: 864562 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4779. Min Act: -0.0000

Data Index: 99399 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4141. Min Act: -0.0000

Data Index: 824952 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4476. Min Act: -0.0000

Data Index: 286534 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4062. Min Act: -0.0000

Data Index: 713098 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1070291 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4172. Min Act: -0.0000

Data Index: 367549 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4002. Min Act: -0.0000

Data Index: 828777 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3963. Min Act: -0.0000

Data Index: 912038 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3992. Min Act: -0.0000

Data Index: 632527 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4329. Min Act: -0.0000

Data Index: 197984 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1071968 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3761. Min Act: -0.0000

Data Index: 551956 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1486862 (Python Code)

Max Activating Token Index: 951

Text #14

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3919. Min Act: -0.0000

Data Index: 856025 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4036. Min Act: -0.0000

Data Index: 758129 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1188683 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4229. Min Act: -0.0000

Data Index: 396447 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3926. Min Act: -0.0000

Data Index: 446183 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3937. Min Act: -0.0000

Data Index: 361500 (C4 (Web Text))

Max Activating Token Index: 1016