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

Dataset: The Pile

Neuron 4650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.5100. Min Act: -0.0000

Data Index: 75563 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.3337. Min Act: -0.0000

Data Index: 1525070 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.6586. Min Act: -0.0000

Data Index: 1381637 (The Pile)

Max Activating Token Index: 207

Text #3

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.4129. Min Act: -0.0000

Data Index: 108333 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1469869 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1420416 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1481281 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1337058 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2926. Min Act: -0.0000

Data Index: 561648 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1049. Min Act: -0.0000

Data Index: 595009 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1779754 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1256904 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1501860 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.0496. Min Act: -0.0000

Data Index: 306722 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1451. Min Act: -0.0000

Data Index: 806726 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1151303 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.0165. Min Act: -0.0000

Data Index: 606812 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 1.7317. Min Range: -1.7317

Max Act: 0.9634. Min Act: -0.0000

Data Index: 190620 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1355338 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 1.7317. Min Range: -1.7317

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1023457 (The Pile)

Max Activating Token Index: 659