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

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

Neuron 2449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3836. Min Range: -2.3836

Max Act: 2.3836. Min Act: -0.0000

Data Index: 907314 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 2.3836. Min Range: -2.3836

Max Act: 2.0970. Min Act: -0.0000

Data Index: 835702 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 2.3836. Min Range: -2.3836

Max Act: 2.1099. Min Act: -0.0000

Data Index: 415628 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.8262. Min Act: -0.0001

Data Index: 765056 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.8980. Min Act: -0.0000

Data Index: 958634 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.8540. Min Act: -0.0000

Data Index: 685798 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.8862. Min Act: -0.0000

Data Index: 838891 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.6558. Min Act: -0.0000

Data Index: 638757 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.7010. Min Act: -0.0000

Data Index: 1305756 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.7197. Min Act: -0.0000

Data Index: 1100532 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.5365. Min Act: -0.0000

Data Index: 738814 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.6230. Min Act: -0.0000

Data Index: 826455 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.6047. Min Act: -0.0000

Data Index: 402648 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.5961. Min Act: -0.0000

Data Index: 656231 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.5085. Min Act: -0.0000

Data Index: 430367 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.5788. Min Act: -0.0000

Data Index: 788629 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.4768. Min Act: -0.0000

Data Index: 70863 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.5538. Min Act: -0.0000

Data Index: 254507 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.4507. Min Act: -0.0000

Data Index: 208841 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.5233. Min Act: 0.0001

Data Index: 1314351 (C4 (Web Text))

Max Activating Token Index: 430