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

Dataset: The Pile

Neuron 481 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0000

Data Index: 977589 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0105. Min Act: -0.0000

Data Index: 895914 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0096. Min Act: -0.0000

Data Index: 1429347 (The Pile)

Max Activating Token Index: 474

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0094. Min Act: -0.0000

Data Index: 1097379 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0097. Min Act: -0.0000

Data Index: 410833 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1526866 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0081. Min Act: -0.0000

Data Index: 1636537 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0077. Min Act: -0.0000

Data Index: 1630713 (The Pile)

Max Activating Token Index: 655

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0086. Min Act: -0.0000

Data Index: 987802 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0092. Min Act: -0.0000

Data Index: 862617 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0084. Min Act: -0.0000

Data Index: 1839131 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0082. Min Act: -0.0000

Data Index: 919950 (The Pile)

Max Activating Token Index: 556

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0079. Min Act: -0.0000

Data Index: 1378872 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1172719 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0082. Min Act: -0.0000

Data Index: 425550 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1972883 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0080. Min Act: -0.0000

Data Index: 1270106 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0079. Min Act: -0.0000

Data Index: 639024 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0077. Min Act: -0.0000

Data Index: 532382 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0079. Min Act: -0.0000

Data Index: 1486063 (The Pile)

Max Activating Token Index: 645