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

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

Neuron 464 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0001

Data Index: 217361 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0578. Min Act: -0.0001

Data Index: 724107 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1286586 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1187918 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0477. Min Act: -0.0001

Data Index: 759329 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0460. Min Act: -0.0001

Data Index: 60062 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0460. Min Act: -0.0001

Data Index: 848694 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1561310 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0441. Min Act: -0.0001

Data Index: 218058 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1108094 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0405. Min Act: -0.0001

Data Index: 956206 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0418. Min Act: -0.0001

Data Index: 835057 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1041746 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0372. Min Act: -0.0001

Data Index: 598450 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0381. Min Act: -0.0001

Data Index: 458214 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1310578 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1651871 (Python Code)

Max Activating Token Index: 688

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0421. Min Act: -0.0001

Data Index: 800830 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0356. Min Act: -0.0001

Data Index: 28760 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1051498 (C4 (Web Text))

Max Activating Token Index: 559