Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1701. Min Act: -0.0000

Data Index: 76466 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1702. Min Act: -0.0001

Data Index: 139092 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1572. Min Act: -0.0000

Data Index: 399707 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1498. Min Act: -0.0001

Data Index: 863064 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1331. Min Act: -0.0001

Data Index: 566637 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1235. Min Act: -0.0000

Data Index: 638283 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1206. Min Act: -0.0001

Data Index: 423862 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1233. Min Act: -0.0001

Data Index: 213231 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1132448 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1340246 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1203. Min Act: -0.0001

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1144. Min Act: -0.0001

Data Index: 164489 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1206. Min Act: -0.0001

Data Index: 585082 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1080. Min Act: -0.0001

Data Index: 506996 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1074. Min Act: -0.0001

Data Index: 961699 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1141. Min Act: -0.0001

Data Index: 364467 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1090. Min Act: -0.0000

Data Index: 31721 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1087. Min Act: -0.0001

Data Index: 744937 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1085. Min Act: -0.0001

Data Index: 6916 (C4 (Web Text))

Max Activating Token Index: 175