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

Dataset: The Pile

Neuron 4853 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.8673. Min Act: -0.0000

Data Index: 938143 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.4865. Min Act: -0.0000

Data Index: 1642362 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.4845. Min Act: -0.0000

Data Index: 1484702 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.6484. Min Act: -0.0000

Data Index: 1176755 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.4760. Min Act: -0.0000

Data Index: 563892 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.2908. Min Act: -0.0000

Data Index: 943439 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.2815. Min Act: -0.0000

Data Index: 1265348 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.4357. Min Act: -0.0000

Data Index: 370156 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.4146. Min Act: -0.0000

Data Index: 471897 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.3754. Min Act: -0.0000

Data Index: 1988668 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.1827. Min Act: -0.0000

Data Index: 1069774 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.3370. Min Act: -0.0000

Data Index: 462023 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.3215. Min Act: -0.0000

Data Index: 512181 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.3161. Min Act: -0.0000

Data Index: 1803781 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.3003. Min Act: -0.0000

Data Index: 1165084 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.2929. Min Act: -0.0000

Data Index: 172874 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.1434. Min Act: -0.0000

Data Index: 814475 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.2623. Min Act: -0.0000

Data Index: 1292274 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.2551. Min Act: -0.0000

Data Index: 1677701 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.2359. Min Act: -0.0000

Data Index: 997225 (The Pile)

Max Activating Token Index: 243