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

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

Neuron 1611 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4501. Min Range: -1.4501

Max Act: 1.4501. Min Act: -0.0000

Data Index: 867120 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 1.4501. Min Range: -1.4501

Max Act: 1.1245. Min Act: -0.0000

Data Index: 930795 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.4501. Min Range: -1.4501

Max Act: 1.1152. Min Act: -0.0000

Data Index: 227755 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.4501. Min Range: -1.4501

Max Act: 1.0735. Min Act: 0.0000

Data Index: 1443784 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 1.4501. Min Range: -1.4501

Max Act: 1.0613. Min Act: -0.0000

Data Index: 318351 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 1.4501. Min Range: -1.4501

Max Act: 1.0458. Min Act: -0.0000

Data Index: 727825 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1414206 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 1.4501. Min Range: -1.4501

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1405302 (Python Code)

Max Activating Token Index: 892

Text #8

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.8835. Min Act: -0.0000

Data Index: 267284 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1520966 (Python Code)

Max Activating Token Index: 574

Text #10

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.9547. Min Act: -0.0000

Data Index: 635838 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1615301 (Python Code)

Max Activating Token Index: 387

Text #12

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1502801 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1363004 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.8351. Min Act: -0.0000

Data Index: 38981 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.8207. Min Act: -0.0000

Data Index: 641526 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1366747 (Python Code)

Max Activating Token Index: 427

Text #17

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1559503 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1532769 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 1.4501. Min Range: -1.4501

Max Act: 0.7771. Min Act: -0.0000

Data Index: 66243 (C4 (Web Text))

Max Activating Token Index: 818