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

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

Neuron 1211 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1365. Min Act: -0.0001

Data Index: 130446 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1143. Min Act: -0.0001

Data Index: 35446 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1278. Min Act: -0.0001

Data Index: 308815 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1287854 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1100. Min Act: -0.0001

Data Index: 157545 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1132. Min Act: -0.0001

Data Index: 427853 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1121. Min Act: -0.0001

Data Index: 73966 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1161950 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1101. Min Act: -0.0000

Data Index: 102554 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1274881 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1100. Min Act: -0.0001

Data Index: 853716 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1250614 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1086. Min Act: -0.0000

Data Index: 788949 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1040. Min Act: -0.0001

Data Index: 536780 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1038. Min Act: -0.0001

Data Index: 329494 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1037. Min Act: -0.0000

Data Index: 667793 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1024. Min Act: -0.0001

Data Index: 631430 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1154139 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1037. Min Act: -0.0001

Data Index: 657611 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1004. Min Act: -0.0001

Data Index: 856475 (C4 (Web Text))

Max Activating Token Index: 966