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

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

Neuron 1360 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1120350 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1413. Min Act: -0.0001

Data Index: 621104 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1408. Min Act: -0.0001

Data Index: 750258 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.0946. Min Act: -0.0001

Data Index: 417020 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1235. Min Act: -0.0001

Data Index: 615839 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1119. Min Act: -0.0001

Data Index: 910845 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1329034 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1111210 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1263. Min Act: -0.0001

Data Index: 991526 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1245. Min Act: -0.0001

Data Index: 449274 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1244. Min Act: -0.0001

Data Index: 214607 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1122. Min Act: -0.0001

Data Index: 969949 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1219. Min Act: -0.0001

Data Index: 884123 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1351053 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1113. Min Act: -0.0001

Data Index: 362330 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.0998. Min Act: -0.0001

Data Index: 593446 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1140. Min Act: -0.0001

Data Index: 175161 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1849 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1105. Min Act: -0.0001

Data Index: 809437 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1060. Min Act: -0.0001

Data Index: 608970 (C4 (Web Text))

Max Activating Token Index: 9