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

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

Neuron 612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.4435. Min Act: -0.0000

Data Index: 1025138 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.5788. Min Act: -0.0000

Data Index: 528416 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.3317. Min Act: -0.0000

Data Index: 1119023 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.1040. Min Act: -0.0000

Data Index: 387572 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.0736. Min Act: -0.0000

Data Index: 360941 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.4129. Min Act: -0.0000

Data Index: 208272 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.2176. Min Act: -0.0000

Data Index: 982 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.1968. Min Act: -0.0000

Data Index: 960845 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.3957. Min Act: -0.0000

Data Index: 511433 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.2154. Min Act: -0.0000

Data Index: 613333 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.4712. Min Act: -0.0000

Data Index: 63605 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.1565. Min Act: -0.0000

Data Index: 431075 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.1419. Min Act: -0.0000

Data Index: 29093 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.2986. Min Act: -0.0000

Data Index: 1352692 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.3030. Min Act: -0.0000

Data Index: 1256168 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.1211. Min Act: -0.0000

Data Index: 320016 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.2621. Min Act: -0.0000

Data Index: 38640 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.2202. Min Act: -0.0000

Data Index: 676828 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.0564. Min Act: -0.0000

Data Index: 1327729 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 4.5788. Min Range: -4.5788

Max Act: 4.3922. Min Act: -0.0000

Data Index: 149097 (C4 (Web Text))

Max Activating Token Index: 855