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

Dataset: The Pile

Neuron 2928 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1255939 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.4424. Min Act: -0.0000

Data Index: 1415223 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.3100. Min Act: -0.0000

Data Index: 1548838 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.3404. Min Act: -0.0001

Data Index: 394987 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.3586. Min Act: -0.0000

Data Index: 844615 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1771663 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1283982 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.2917. Min Act: -0.0000

Data Index: 449604 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.1918. Min Act: -0.0000

Data Index: 341368 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1221073 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.1416. Min Act: -0.0000

Data Index: 1840324 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.2210. Min Act: -0.0000

Data Index: 377395 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.3218. Min Act: -0.0000

Data Index: 378014 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.1808. Min Act: -0.0000

Data Index: 858767 (The Pile)

Max Activating Token Index: 470

Text #14

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1140479 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.1379. Min Act: -0.0000

Data Index: 857655 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 1.7561. Min Range: -1.7561

Max Act: 0.9809. Min Act: -0.0000

Data Index: 335150 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1407843 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 1.7561. Min Range: -1.7561

Max Act: 0.9833. Min Act: -0.0000

Data Index: 775820 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 1.7561. Min Range: -1.7561

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1430753 (The Pile)

Max Activating Token Index: 138