Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5395 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1054. Min Range: -2.1054

Max Act: 2.1054. Min Act: -0.0000

Data Index: 59804 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8527. Min Act: -0.0000

Data Index: 111191 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.9703. Min Act: -0.0000

Data Index: 435822 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 2.1054. Min Range: -2.1054

Max Act: 2.0220. Min Act: -0.0000

Data Index: 394037 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8868. Min Act: -0.0000

Data Index: 474484 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.9949. Min Act: -0.0000

Data Index: 678084 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8758. Min Act: -0.0000

Data Index: 568053 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8276. Min Act: -0.0000

Data Index: 745938 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7208. Min Act: -0.0000

Data Index: 709616 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7808. Min Act: -0.0000

Data Index: 18425 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.9210. Min Act: -0.0000

Data Index: 427423 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1194573 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1116089 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1178209 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.6875. Min Act: -0.0000

Data Index: 1239456 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.5944. Min Act: -0.0000

Data Index: 1314941 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.6750. Min Act: -0.0000

Data Index: 384914 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8848. Min Act: -0.0000

Data Index: 1007108 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7475. Min Act: -0.0000

Data Index: 3507 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1053383 (C4 (Web Text))

Max Activating Token Index: 298