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

Dataset: The Pile

Neuron 2895 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: 4.8120. Min Range: -4.8120

Max Act: 4.1803. Min Act: -0.0000

Data Index: 691394 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.4255. Min Act: -0.0000

Data Index: 146107 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.1064. Min Act: -0.0000

Data Index: 1706773 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.8120. Min Act: -0.0000

Data Index: 456224 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.5220. Min Act: -0.0000

Data Index: 1161644 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.7919. Min Act: -0.0000

Data Index: 1231845 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.8873. Min Act: -0.0000

Data Index: 1495099 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.2490. Min Act: -0.0000

Data Index: 23894 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.8810. Min Act: -0.0000

Data Index: 1308066 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.3793. Min Act: -0.0000

Data Index: 786789 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.6125. Min Act: -0.0000

Data Index: 1319458 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.3198. Min Act: -0.0000

Data Index: 600493 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.7789. Min Act: -0.0000

Data Index: 1363517 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.5990. Min Act: -0.0000

Data Index: 457172 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.2848. Min Act: -0.0000

Data Index: 1594501 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.8525. Min Act: -0.0000

Data Index: 1446899 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 4.8120. Min Range: -4.8120

Max Act: 4.2833. Min Act: -0.0000

Data Index: 405263 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.8934. Min Act: -0.0000

Data Index: 1376107 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.6902. Min Act: -0.0000

Data Index: 1068130 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 4.8120. Min Range: -4.8120

Max Act: 3.8769. Min Act: -0.0000

Data Index: 775563 (The Pile)

Max Activating Token Index: 491