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

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

Neuron 3832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 55184 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1047. Min Act: -0.0001

Data Index: 918279 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1029. Min Act: -0.0001

Data Index: 576218 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0973. Min Act: -0.0000

Data Index: 916488 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1157976 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0961. Min Act: -0.0001

Data Index: 35430 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0933. Min Act: -0.0001

Data Index: 160673 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0952. Min Act: -0.0001

Data Index: 174849 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0949. Min Act: -0.0001

Data Index: 807884 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0944. Min Act: -0.0000

Data Index: 887673 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0878. Min Act: -0.0001

Data Index: 496706 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0933. Min Act: -0.0001

Data Index: 454179 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0936. Min Act: -0.0000

Data Index: 358726 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0902. Min Act: -0.0001

Data Index: 96540 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1334899 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0928. Min Act: -0.0001

Data Index: 29360 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0902. Min Act: -0.0000

Data Index: 722804 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1338151 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0869. Min Act: -0.0000

Data Index: 631826 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1141755 (C4 (Web Text))

Max Activating Token Index: 447