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

Dataset: The Pile

Neuron 629 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.7094. Min Act: -0.0000

Data Index: 1803843 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.7071. Min Act: -0.0000

Data Index: 892553 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.6452. Min Act: -0.0000

Data Index: 459782 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1480282 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4406. Min Act: -0.0000

Data Index: 1273817 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5546. Min Act: -0.0000

Data Index: 774683 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2170. Min Act: -0.0000

Data Index: 239724 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1797897 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.1143. Min Act: -0.0000

Data Index: 516171 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1374800 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.9923. Min Act: -0.0000

Data Index: 932104 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1427455 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.9985. Min Act: -0.0000

Data Index: 50171 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.9262. Min Act: -0.0000

Data Index: 407584 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.9068. Min Act: -0.0000

Data Index: 851332 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1993565 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.0369. Min Act: -0.0000

Data Index: 1965829 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1227404 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1541519 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 1.7094. Min Range: -1.7094

Max Act: 0.8529. Min Act: -0.0000

Data Index: 583207 (The Pile)

Max Activating Token Index: 757