Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2650 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1328976 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4371. Min Act: -0.0000

Data Index: 268299 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3852. Min Act: -0.0000

Data Index: 903898 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1007448 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4177. Min Act: -0.0000

Data Index: 458060 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1162962 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3752. Min Act: -0.0000

Data Index: 564347 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3525. Min Act: -0.0000

Data Index: 295994 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3408. Min Act: -0.0000

Data Index: 612838 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3245. Min Act: -0.0000

Data Index: 400322 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3470. Min Act: -0.0000

Data Index: 258997 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2975. Min Act: -0.0000

Data Index: 224943 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3162. Min Act: -0.0000

Data Index: 801501 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3118. Min Act: -0.0000

Data Index: 161713 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3093. Min Act: -0.0000

Data Index: 828537 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1025750 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1350035 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3333. Min Act: -0.0000

Data Index: 390745 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3176. Min Act: -0.0000

Data Index: 447800 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2968. Min Act: -0.0000

Data Index: 976180 (C4 (Web Text))

Max Activating Token Index: 266