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

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

Neuron 636 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: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0001

Data Index: 778863 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1332308 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1011. Min Act: -0.0001

Data Index: 802180 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0984. Min Act: -0.0001

Data Index: 593930 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1047969 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1086. Min Act: -0.0001

Data Index: 916752 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0988. Min Act: -0.0001

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0940. Min Act: -0.0002

Data Index: 509824 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1040. Min Act: -0.0002

Data Index: 768690 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0918. Min Act: -0.0001

Data Index: 296019 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1010533 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0899. Min Act: -0.0001

Data Index: 888287 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1013164 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1085375 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0936. Min Act: -0.0001

Data Index: 351807 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1351461 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0860. Min Act: -0.0002

Data Index: 158229 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0860. Min Act: -0.0001

Data Index: 868676 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1149611 (C4 (Web Text))

Max Activating Token Index: 994