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

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

Neuron 2520 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.5493. Min Act: -0.0000

Data Index: 850309 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.5664. Min Act: -0.0000

Data Index: 29209 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1051670 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.5069. Min Act: -0.0000

Data Index: 19255 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4867. Min Act: -0.0000

Data Index: 39830 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4533. Min Act: -0.0000

Data Index: 135009 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3922. Min Act: -0.0000

Data Index: 525300 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4101. Min Act: -0.0000

Data Index: 215589 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1158851 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3973. Min Act: -0.0000

Data Index: 192498 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3719. Min Act: -0.0000

Data Index: 2404 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3606. Min Act: -0.0000

Data Index: 456652 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3791. Min Act: -0.0000

Data Index: 801537 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1079567 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3470. Min Act: -0.0000

Data Index: 954852 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3355. Min Act: -0.0000

Data Index: 954977 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3282. Min Act: -0.0000

Data Index: 610146 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1283204 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3161. Min Act: 0.0000

Data Index: 883304 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3354. Min Act: -0.0000

Data Index: 717038 (C4 (Web Text))

Max Activating Token Index: 358