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

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

Neuron 1095 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.9118. Min Act: -0.0000

Data Index: 102454 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.8757. Min Act: -0.0000

Data Index: 169895 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.7598. Min Act: -0.0000

Data Index: 211208 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5098. Min Act: -0.0000

Data Index: 538113 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5948. Min Act: -0.0000

Data Index: 430060 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.6811. Min Act: -0.0000

Data Index: 702446 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5809. Min Act: -0.0000

Data Index: 620567 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.6606. Min Act: -0.0000

Data Index: 1308506 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5558. Min Act: 0.0000

Data Index: 586338 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1014568 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.4414. Min Act: -0.0000

Data Index: 492027 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5616. Min Act: 0.0000

Data Index: 626927 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.4816. Min Act: -0.0000

Data Index: 125196 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3907. Min Act: -0.0000

Data Index: 1009923 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.4228. Min Act: 0.0000

Data Index: 170654 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3863. Min Act: 0.0000

Data Index: 2187 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.4604. Min Act: -0.0000

Data Index: 1153342 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3732. Min Act: -0.0000

Data Index: 58722 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1295307 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.4327. Min Act: -0.0000

Data Index: 827421 (C4 (Web Text))

Max Activating Token Index: 77