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

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

Neuron 92 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.7849. Min Act: 0.0000

Data Index: 1509661 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1403433 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1559015 (Python Code)

Max Activating Token Index: 951

Text #3

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1574462 (Python Code)

Max Activating Token Index: 855

Text #4

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1540068 (Python Code)

Max Activating Token Index: 941

Text #5

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1426754 (Python Code)

Max Activating Token Index: 863

Text #6

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1407172 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1404481 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1583203 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1626889 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6254. Min Act: 0.0000

Data Index: 1484153 (Python Code)

Max Activating Token Index: 693

Text #11

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1636313 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1554522 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1144401 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1465966 (Python Code)

Max Activating Token Index: 444

Text #15

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1437186 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1518349 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1601404 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6252. Min Act: 0.0000

Data Index: 1382385 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1506446 (Python Code)

Max Activating Token Index: 788