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

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

Neuron 3380 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.6709. Min Act: -0.0001

Data Index: 798218 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5893. Min Act: -0.0001

Data Index: 454443 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5746. Min Act: -0.0001

Data Index: 494455 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.6009. Min Act: -0.0001

Data Index: 1266790 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5502. Min Act: -0.0001

Data Index: 541280 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.6034. Min Act: -0.0001

Data Index: 1154137 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5416. Min Act: -0.0001

Data Index: 900060 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.6320. Min Act: -0.0001

Data Index: 1079929 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5768. Min Act: -0.0001

Data Index: 792156 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5857. Min Act: -0.0001

Data Index: 454817 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5287. Min Act: -0.0001

Data Index: 1137806 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.4998. Min Act: -0.0001

Data Index: 153972 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.4509. Min Act: -0.0001

Data Index: 264925 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5206. Min Act: -0.0001

Data Index: 56460 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.4582. Min Act: -0.0001

Data Index: 160829 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.4652. Min Act: -0.0001

Data Index: 613677 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.5072. Min Act: -0.0001

Data Index: 1197951 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.4880. Min Act: -0.0001

Data Index: 496347 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.3928. Min Act: -0.0001

Data Index: 1236741 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 1.6709. Min Range: -1.6709

Max Act: 1.4729. Min Act: -0.0001

Data Index: 953349 (C4 (Web Text))

Max Activating Token Index: 515