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

Dataset: The Pile

Neuron 3801 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: 3.4612. Min Range: -3.4612

Max Act: 3.4612. Min Act: -0.0000

Data Index: 1572536 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3705. Min Act: -0.0000

Data Index: 1892661 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.0631. Min Act: -0.0000

Data Index: 546618 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1249. Min Act: -0.0000

Data Index: 1373232 (The Pile)

Max Activating Token Index: 342

Text #4

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1799. Min Act: -0.0000

Data Index: 1408254 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8990. Min Act: -0.0000

Data Index: 982617 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.0235. Min Act: -0.0000

Data Index: 414812 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8875. Min Act: -0.0000

Data Index: 797207 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.0120. Min Act: -0.0000

Data Index: 1788550 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.9560. Min Act: -0.0000

Data Index: 1914068 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8977. Min Act: -0.0000

Data Index: 1353407 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.7698. Min Act: -0.0000

Data Index: 1588894 (The Pile)

Max Activating Token Index: 871

Text #12

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8813. Min Act: -0.0000

Data Index: 1784607 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8806. Min Act: -0.0000

Data Index: 1797333 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8658. Min Act: -0.0000

Data Index: 1868319 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.7150. Min Act: -0.0000

Data Index: 909992 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8641. Min Act: -0.0000

Data Index: 378502 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.7730. Min Act: -0.0000

Data Index: 1088772 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.6033. Min Act: -0.0000

Data Index: 1200170 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 3.4612. Min Range: -3.4612

Max Act: 2.8712. Min Act: -0.0000

Data Index: 990785 (The Pile)

Max Activating Token Index: 547