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

Dataset: The Pile

Neuron 1669 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: 0.5986. Min Range: -0.5986

Max Act: 0.5972. Min Act: -0.0000

Data Index: 213298 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5986. Min Act: -0.0000

Data Index: 881134 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5782. Min Act: -0.0000

Data Index: 769803 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1381386 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5075. Min Act: -0.0000

Data Index: 145066 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1529040 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1549619 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4968. Min Act: -0.0000

Data Index: 744011 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4696. Min Act: -0.0000

Data Index: 66957 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1818035 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4799. Min Act: -0.0000

Data Index: 20197 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5366. Min Act: -0.0000

Data Index: 67898 (The Pile)

Max Activating Token Index: 139

Text #12

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4413. Min Act: -0.0000

Data Index: 331270 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1463650 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1954968 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4256. Min Act: -0.0000

Data Index: 340934 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1342006 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1073977 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1874081 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4556. Min Act: -0.0000

Data Index: 138004 (The Pile)

Max Activating Token Index: 256