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

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

Neuron 1005 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0570. Min Act: -0.0001

Data Index: 1611600 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9843. Min Act: -0.0001

Data Index: 1224357 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9108. Min Act: -0.0001

Data Index: 573400 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9543. Min Act: -0.0001

Data Index: 1378304 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8834. Min Act: -0.0001

Data Index: 33604 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9102. Min Act: -0.0001

Data Index: 1656286 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1459742 (Python Code)

Max Activating Token Index: 716

Text #7

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8205. Min Act: -0.0001

Data Index: 1121106 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8689. Min Act: -0.0001

Data Index: 1510270 (Python Code)

Max Activating Token Index: 786

Text #9

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9776. Min Act: -0.0001

Data Index: 945465 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8844. Min Act: -0.0001

Data Index: 1435800 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8222. Min Act: -0.0001

Data Index: 1158448 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9087. Min Act: -0.0001

Data Index: 440047 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8953. Min Act: -0.0001

Data Index: 968119 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8215. Min Act: -0.0001

Data Index: 1473075 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1504816 (Python Code)

Max Activating Token Index: 331

Text #16

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8467. Min Act: -0.0001

Data Index: 1386033 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1456465 (Python Code)

Max Activating Token Index: 685

Text #18

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7722. Min Act: -0.0001

Data Index: 1626610 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1556073 (Python Code)

Max Activating Token Index: 566