Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2323 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1705874 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2710. Min Act: -0.0000

Data Index: 798537 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2651. Min Act: -0.0000

Data Index: 82643 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2595. Min Act: -0.0000

Data Index: 816304 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1463629 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1292034 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1629489 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2026. Min Act: -0.0000

Data Index: 357352 (The Pile)

Max Activating Token Index: 933

Text #8

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2159. Min Act: -0.0000

Data Index: 898262 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1467337 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2035. Min Act: -0.0000

Data Index: 348433 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1367435 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2206. Min Act: -0.0000

Data Index: 56554 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1019908 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1464285 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2094. Min Act: -0.0000

Data Index: 423899 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1659523 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1780718 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.2207. Min Act: -0.0000

Data Index: 663761 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.2710. Min Range: -0.2710

Max Act: 0.1974. Min Act: -0.0000

Data Index: 961667 (The Pile)

Max Activating Token Index: 486