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

Dataset: The Pile

Neuron 1564 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: 1.9749. Min Range: -1.9749

Max Act: 1.8972. Min Act: -0.0000

Data Index: 1731188 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.9749. Min Act: -0.0000

Data Index: 157033 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.8103. Min Act: -0.0000

Data Index: 622388 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1218490 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.9353. Min Act: -0.0000

Data Index: 1313141 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.7180. Min Act: -0.0000

Data Index: 905971 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1936716 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6616. Min Act: -0.0000

Data Index: 445797 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6941. Min Act: -0.0000

Data Index: 1531210 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.7500. Min Act: -0.0000

Data Index: 594620 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.8131. Min Act: -0.0000

Data Index: 959872 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6836. Min Act: -0.0000

Data Index: 801690 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.8369. Min Act: -0.0000

Data Index: 510244 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6386. Min Act: -0.0000

Data Index: 1196699 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6362. Min Act: -0.0000

Data Index: 1624291 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6260. Min Act: -0.0000

Data Index: 1442853 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.7259. Min Act: -0.0000

Data Index: 949347 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1911538 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.8446. Min Act: -0.0000

Data Index: 754689 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6770. Min Act: -0.0000

Data Index: 1845120 (The Pile)

Max Activating Token Index: 123