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

Dataset: The Pile

Neuron 2440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3332. Min Act: -0.0000

Data Index: 911994 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3006. Min Act: -0.0000

Data Index: 927755 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2685. Min Act: -0.0000

Data Index: 232879 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2352. Min Act: -0.0000

Data Index: 704229 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1523417 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2323. Min Act: -0.0000

Data Index: 65563 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2172. Min Act: -0.0000

Data Index: 910998 (The Pile)

Max Activating Token Index: 274

Text #7

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2142. Min Act: -0.0000

Data Index: 263322 (The Pile)

Max Activating Token Index: 754

Text #8

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1597293 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2127. Min Act: -0.0000

Data Index: 145499 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1755207 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1269225 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1667686 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2208. Min Act: -0.0000

Data Index: 810534 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1043217 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1940525 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2157. Min Act: -0.0000

Data Index: 265382 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2164. Min Act: -0.0000

Data Index: 446019 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.1918. Min Act: -0.0000

Data Index: 505940 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2117. Min Act: -0.0000

Data Index: 907060 (The Pile)

Max Activating Token Index: 488