Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 79 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.4097. Min Act: -0.0001

Data Index: 290566 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3550. Min Act: -0.0001

Data Index: 891862 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3915. Min Act: -0.0001

Data Index: 564157 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3266. Min Act: -0.0001

Data Index: 250883 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3299. Min Act: -0.0001

Data Index: 258950 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3126. Min Act: -0.0001

Data Index: 1314473 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3024. Min Act: -0.0001

Data Index: 864707 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3074. Min Act: -0.0001

Data Index: 993145 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3055. Min Act: -0.0001

Data Index: 978057 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1177174 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2988. Min Act: -0.0001

Data Index: 193186 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3163. Min Act: -0.0001

Data Index: 22176 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3046. Min Act: -0.0001

Data Index: 126004 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3141. Min Act: -0.0001

Data Index: 851299 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3044. Min Act: -0.0001

Data Index: 762634 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1139391 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3025. Min Act: -0.0001

Data Index: 475099 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2994. Min Act: -0.0001

Data Index: 332554 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1155545 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3190. Min Act: -0.0001

Data Index: 25302 (C4 (Web Text))

Max Activating Token Index: 248