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

Dataset: The Pile

Neuron 2703 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: 0.6795. Min Range: -0.6795

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1757678 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5703. Min Act: -0.0000

Data Index: 846295 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5840. Min Act: -0.0000

Data Index: 257533 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5550. Min Act: -0.0000

Data Index: 864867 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1289926 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5667. Min Act: -0.0000

Data Index: 876581 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5433. Min Act: -0.0000

Data Index: 352269 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1711775 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1143584 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1834945 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1017629 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1573308 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1927657 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1990582 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1948546 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1120860 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1884448 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4918. Min Act: -0.0000

Data Index: 581060 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5052. Min Act: -0.0000

Data Index: 385146 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1494187 (The Pile)

Max Activating Token Index: 645