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

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

Neuron 3258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0001

Data Index: 76245 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1259874 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1003. Min Act: -0.0001

Data Index: 180704 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1036. Min Act: -0.0001

Data Index: 371675 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0980. Min Act: -0.0001

Data Index: 810764 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1264728 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1126645 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1143757 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1129838 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0919. Min Act: -0.0001

Data Index: 221574 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0961. Min Act: -0.0001

Data Index: 753727 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0926. Min Act: -0.0001

Data Index: 401551 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0957. Min Act: -0.0001

Data Index: 239451 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0955. Min Act: -0.0001

Data Index: 666981 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0952. Min Act: -0.0001

Data Index: 183706 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0956. Min Act: -0.0001

Data Index: 838174 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0944. Min Act: -0.0001

Data Index: 968311 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0941. Min Act: -0.0001

Data Index: 253076 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0937. Min Act: -0.0001

Data Index: 963430 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0906. Min Act: -0.0001

Data Index: 79454 (C4 (Web Text))

Max Activating Token Index: 917