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

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

Neuron 3521 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: 0.1801. Min Range: -0.1801

Max Act: 0.1801. Min Act: -0.0002

Data Index: 744337 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1017. Min Act: -0.0001

Data Index: 211176 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1051. Min Act: -0.0001

Data Index: 982606 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1243293 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1093. Min Act: -0.0001

Data Index: 593905 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1028. Min Act: -0.0001

Data Index: 551804 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1018. Min Act: -0.0001

Data Index: 288446 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1046. Min Act: -0.0001

Data Index: 709147 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1289001 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0993. Min Act: -0.0002

Data Index: 337991 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0950. Min Act: -0.0001

Data Index: 353458 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1013. Min Act: -0.0001

Data Index: 87231 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0950. Min Act: -0.0001

Data Index: 603488 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0940. Min Act: -0.0001

Data Index: 433620 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0923. Min Act: -0.0001

Data Index: 399796 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0993. Min Act: -0.0002

Data Index: 126638 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0891. Min Act: -0.0001

Data Index: 538178 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0983. Min Act: -0.0002

Data Index: 374308 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0917. Min Act: -0.0001

Data Index: 42020 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0793. Min Act: -0.0001

Data Index: 801335 (C4 (Web Text))

Max Activating Token Index: 578