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

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

Neuron 1037 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: 0.1572. Min Range: -0.1572

Max Act: 0.1572. Min Act: -0.0001

Data Index: 882057 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1453. Min Act: -0.0001

Data Index: 511384 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1445. Min Act: -0.0001

Data Index: 919719 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1461. Min Act: -0.0001

Data Index: 985020 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1531. Min Act: -0.0001

Data Index: 755254 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1241. Min Act: -0.0001

Data Index: 787597 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1243. Min Act: -0.0001

Data Index: 85150 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1232. Min Act: -0.0001

Data Index: 990208 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1013970 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1219. Min Act: -0.0001

Data Index: 684821 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1257277 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1153. Min Act: -0.0001

Data Index: 914469 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1197. Min Act: -0.0001

Data Index: 849418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1221. Min Act: -0.0001

Data Index: 730420 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1209. Min Act: -0.0001

Data Index: 243746 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1073. Min Act: -0.0001

Data Index: 401550 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1173. Min Act: -0.0001

Data Index: 716415 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1120. Min Act: -0.0001

Data Index: 140483 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1000506 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1132. Min Act: -0.0001

Data Index: 289357 (C4 (Web Text))

Max Activating Token Index: 593