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

Dataset: The Pile

Neuron 1136 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: 5.0168. Min Range: -5.0168

Max Act: 5.0168. Min Act: -0.0000

Data Index: 1987431 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 5.0168. Min Range: -5.0168

Max Act: 3.9265. Min Act: -0.0000

Data Index: 171283 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.5974. Min Act: -0.0000

Data Index: 886513 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.4969. Min Act: -0.0000

Data Index: 1819870 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.0836. Min Act: -0.0000

Data Index: 1342894 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.2450. Min Act: -0.0000

Data Index: 1003789 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.1563. Min Act: -0.0000

Data Index: 818744 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.2389. Min Act: -0.0000

Data Index: 433007 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.2344. Min Act: -0.0000

Data Index: 85315 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.1896. Min Act: -0.0000

Data Index: 545335 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.0385. Min Act: -0.0000

Data Index: 1971061 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.3794. Min Act: -0.0000

Data Index: 1947843 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.2152. Min Act: -0.0000

Data Index: 828645 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.4158. Min Act: -0.0000

Data Index: 244618 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.3994. Min Act: -0.0000

Data Index: 1443899 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 5.0168. Min Range: -5.0168

Max Act: 4.3717. Min Act: -0.0000

Data Index: 1166435 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 5.0168. Min Range: -5.0168

Max Act: 3.8420. Min Act: -0.0000

Data Index: 985222 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 5.0168. Min Range: -5.0168

Max Act: 3.9691. Min Act: -0.0000

Data Index: 964292 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 5.0168. Min Range: -5.0168

Max Act: 3.9621. Min Act: -0.0000

Data Index: 1546919 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 5.0168. Min Range: -5.0168

Max Act: 3.9014. Min Act: -0.0000

Data Index: 1019384 (The Pile)

Max Activating Token Index: 156