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

Dataset: The Pile

Neuron 1251 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: 3.8114. Min Range: -3.8114

Max Act: 3.8114. Min Act: -0.0000

Data Index: 1711780 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 3.8114. Min Range: -3.8114

Max Act: 3.7728. Min Act: -0.0000

Data Index: 391891 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 3.8114. Min Range: -3.8114

Max Act: 3.1887. Min Act: -0.0000

Data Index: 1169923 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.8983. Min Act: -0.0000

Data Index: 1876934 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.4966. Min Act: -0.0000

Data Index: 1230260 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.6940. Min Act: -0.0000

Data Index: 234684 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1571642 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1695851 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.8056. Min Act: -0.0000

Data Index: 1991552 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.5326. Min Act: -0.0000

Data Index: 1924633 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.4060. Min Act: -0.0000

Data Index: 896114 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.6537. Min Act: -0.0000

Data Index: 1660851 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.6430. Min Act: -0.0000

Data Index: 1175456 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.4382. Min Act: -0.0000

Data Index: 1411214 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.5598. Min Act: -0.0000

Data Index: 851947 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1689665 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.4397. Min Act: -0.0000

Data Index: 1138517 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.4415. Min Act: -0.0000

Data Index: 1076937 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.3995. Min Act: -0.0000

Data Index: 362067 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 3.8114. Min Range: -3.8114

Max Act: 2.3698. Min Act: -0.0000

Data Index: 634246 (The Pile)

Max Activating Token Index: 526