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

Dataset: The Pile

Neuron 4398 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: 3.1309. Min Range: -3.1309

Max Act: 3.1309. Min Act: -0.0000

Data Index: 444291 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.8897. Min Act: -0.0000

Data Index: 1444020 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 3.1309. Min Range: -3.1309

Max Act: 3.0067. Min Act: -0.0000

Data Index: 1925450 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.7033. Min Act: -0.0000

Data Index: 1392821 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.8225. Min Act: -0.0000

Data Index: 1480392 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.6164. Min Act: -0.0000

Data Index: 1207423 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.8845. Min Act: -0.0000

Data Index: 1335396 (The Pile)

Max Activating Token Index: 730

Text #7

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.8373. Min Act: -0.0000

Data Index: 899490 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.7128. Min Act: -0.0000

Data Index: 1057210 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.6803. Min Act: -0.0000

Data Index: 244412 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.9633. Min Act: -0.0000

Data Index: 1271670 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.7897. Min Act: -0.0000

Data Index: 1632320 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.6329. Min Act: -0.0000

Data Index: 1711902 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.8682. Min Act: -0.0000

Data Index: 662318 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.7187. Min Act: -0.0000

Data Index: 1196982 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.7181. Min Act: -0.0000

Data Index: 601306 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.6698. Min Act: -0.0000

Data Index: 1968868 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.6811. Min Act: -0.0000

Data Index: 1847115 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.8219. Min Act: -0.0000

Data Index: 1699535 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 3.1309. Min Range: -3.1309

Max Act: 2.5573. Min Act: -0.0000

Data Index: 961982 (The Pile)

Max Activating Token Index: 570