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

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

Neuron 3227 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0000

Data Index: 218119 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1213. Min Act: -0.0001

Data Index: 220163 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1026044 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1132. Min Act: -0.0000

Data Index: 367208 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1090083 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1119. Min Act: -0.0000

Data Index: 14625 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1120. Min Act: -0.0001

Data Index: 869606 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1065. Min Act: -0.0000

Data Index: 249525 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1057. Min Act: -0.0001

Data Index: 446348 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1064. Min Act: -0.0001

Data Index: 331415 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0997. Min Act: -0.0000

Data Index: 92338 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1024. Min Act: -0.0001

Data Index: 513650 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1016. Min Act: -0.0000

Data Index: 993588 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0935. Min Act: -0.0000

Data Index: 525893 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1251655 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0908. Min Act: -0.0000

Data Index: 83164 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0939. Min Act: -0.0000

Data Index: 494260 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0964. Min Act: -0.0000

Data Index: 790118 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1186419 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1328475 (C4 (Web Text))

Max Activating Token Index: 231