Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3312 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.6009. Min Act: -0.0000

Data Index: 1405199 (Python Code)

Max Activating Token Index: 196

Text #1

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.3974. Min Act: -0.0000

Data Index: 1492897 (Python Code)

Max Activating Token Index: 1000

Text #2

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.6561. Min Act: -0.0000

Data Index: 1394561 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.1857. Min Act: -0.0000

Data Index: 1515646 (Python Code)

Max Activating Token Index: 223

Text #4

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.4337. Min Act: -0.0000

Data Index: 1653584 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.4217. Min Act: -0.0000

Data Index: 1481152 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.4287. Min Act: -0.0000

Data Index: 1525619 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.4145. Min Act: -0.0000

Data Index: 1568357 (Python Code)

Max Activating Token Index: 469

Text #8

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.4164. Min Act: -0.0000

Data Index: 1502337 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.4007. Min Act: -0.0000

Data Index: 1401871 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.2831. Min Act: -0.0000

Data Index: 1541145 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.2514. Min Act: -0.0000

Data Index: 1418840 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.6659. Min Act: -0.0000

Data Index: 1365438 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.3669. Min Act: -0.0000

Data Index: 1579065 (Python Code)

Max Activating Token Index: 696

Text #14

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.3458. Min Act: -0.0000

Data Index: 1439774 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.3362. Min Act: -0.0000

Data Index: 14117 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.3482. Min Act: -0.0000

Data Index: 1566856 (Python Code)

Max Activating Token Index: 986

Text #17

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.2082. Min Act: -0.0000

Data Index: 1363215 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.3228. Min Act: -0.0000

Data Index: 1594514 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 2.6659. Min Range: -2.6659

Max Act: 2.3164. Min Act: -0.0000

Data Index: 1415316 (Python Code)

Max Activating Token Index: 561