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

Dataset: The Pile

Neuron 3346 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1083015 (The Pile)

Max Activating Token Index: 285

Text #1

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2117. Min Act: -0.0000

Data Index: 406818 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2141. Min Act: -0.0000

Data Index: 382583 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1525368 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1746313 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2054. Min Act: -0.0000

Data Index: 178720 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1700798 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1785735 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1302150 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1986. Min Act: -0.0000

Data Index: 586436 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1944. Min Act: -0.0000

Data Index: 884207 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1878. Min Act: -0.0000

Data Index: 968522 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1048047 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1877. Min Act: -0.0000

Data Index: 310514 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1884. Min Act: -0.0000

Data Index: 63605 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1786. Min Act: -0.0000

Data Index: 933065 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1857. Min Act: -0.0000

Data Index: 338732 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1225260 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1115495 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1875. Min Act: -0.0000

Data Index: 841388 (The Pile)

Max Activating Token Index: 191