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

Dataset: The Pile

Neuron 748 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: 0.2637. Min Range: -0.2637

Max Act: 0.2637. Min Act: 0.0000

Data Index: 1190636 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2520. Min Act: 0.0000

Data Index: 1802366 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1005378 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2597. Min Act: 0.0000

Data Index: 1043221 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1193001 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2341. Min Act: 0.0000

Data Index: 1274224 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1476314 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2204. Min Act: 0.0000

Data Index: 1650709 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2102. Min Act: 0.0000

Data Index: 1116083 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2102. Min Act: -0.0000

Data Index: 735036 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1021323 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1365472 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1412960 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1966899 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2136. Min Act: 0.0000

Data Index: 1523219 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2028. Min Act: 0.0000

Data Index: 539861 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2110. Min Act: -0.0000

Data Index: 596343 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2058. Min Act: 0.0000

Data Index: 36068 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1565894 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1650934 (The Pile)

Max Activating Token Index: 518