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

Dataset: The Pile

Neuron 102 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1040589 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.3105. Min Act: -0.0000

Data Index: 599764 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.3215. Min Act: -0.0000

Data Index: 296351 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1145904 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2526. Min Act: -0.0000

Data Index: 701797 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2453. Min Act: -0.0000

Data Index: 921286 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2591. Min Act: -0.0000

Data Index: 923405 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2531. Min Act: -0.0000

Data Index: 551909 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1221006 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1040266 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2120. Min Act: -0.0000

Data Index: 131215 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2097. Min Act: -0.0000

Data Index: 750434 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1639430 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1008066 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2366. Min Act: -0.0000

Data Index: 626346 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2088. Min Act: -0.0000

Data Index: 879455 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1475565 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1829772 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2036. Min Act: -0.0000

Data Index: 618329 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.1936. Min Act: -0.0000

Data Index: 859638 (The Pile)

Max Activating Token Index: 527