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

Dataset: The Pile

Neuron 1485 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: 1.7140. Min Range: -1.7140

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1243787 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5587. Min Act: -0.0000

Data Index: 1210394 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1151359 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4201. Min Act: -0.0000

Data Index: 393773 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3843. Min Act: -0.0000

Data Index: 1315971 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3651. Min Act: -0.0000

Data Index: 1871522 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1615842 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1486247 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3503. Min Act: -0.0000

Data Index: 687030 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3515. Min Act: -0.0000

Data Index: 789827 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2059. Min Act: -0.0000

Data Index: 978620 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2545. Min Act: -0.0000

Data Index: 164508 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3416. Min Act: -0.0000

Data Index: 469368 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2711. Min Act: -0.0000

Data Index: 70426 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2398. Min Act: -0.0000

Data Index: 761561 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1254078 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2225. Min Act: -0.0000

Data Index: 792098 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2769. Min Act: -0.0001

Data Index: 1059141 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2498. Min Act: -0.0000

Data Index: 513889 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1016709 (The Pile)

Max Activating Token Index: 103