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

Dataset: The Pile

Neuron 4360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.5363. Min Act: -0.0000

Data Index: 834954 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1255004 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.4152. Min Act: -0.0000

Data Index: 1604496 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.5455. Min Act: -0.0000

Data Index: 801009 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1703534 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.4392. Min Act: -0.0000

Data Index: 652443 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1066743 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1956778 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1035067 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1033029 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1263812 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1883319 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.2872. Min Act: -0.0000

Data Index: 362620 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1706223 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1804332 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1769485 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1472068 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1058. Min Act: -0.0000

Data Index: 253529 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1756. Min Act: -0.0000

Data Index: 1518853 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1398125 (The Pile)

Max Activating Token Index: 543