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

Dataset: The Pile

Neuron 1240 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: 1.7814. Min Range: -1.7814

Max Act: 1.7814. Min Act: 0.0000

Data Index: 653090 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.7393. Min Act: -0.0000

Data Index: 969255 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.4981. Min Act: -0.0000

Data Index: 425474 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1681052 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.3064. Min Act: -0.0000

Data Index: 952149 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2372. Min Act: -0.0000

Data Index: 934304 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.3755. Min Act: -0.0000

Data Index: 1200579 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1214562 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1851225 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.3375. Min Act: -0.0000

Data Index: 897023 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1257136 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1057182 (The Pile)

Max Activating Token Index: 763

Text #12

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2700. Min Act: -0.0000

Data Index: 1629496 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1398576 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1345514 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.1987. Min Act: -0.0000

Data Index: 990406 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.1902. Min Act: -0.0000

Data Index: 159953 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.1988. Min Act: -0.0000

Data Index: 870223 (The Pile)

Max Activating Token Index: 213

Text #18

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1958892 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 1.7814. Min Range: -1.7814

Max Act: 1.2008. Min Act: -0.0000

Data Index: 415133 (The Pile)

Max Activating Token Index: 874