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

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

Neuron 1238 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: 4.1919. Min Range: -4.1919

Max Act: 4.1919. Min Act: -0.0001

Data Index: 265194 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8635. Min Act: -0.0000

Data Index: 1305007 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.6991. Min Act: -0.0000

Data Index: 1314659 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.4993. Min Act: -0.0000

Data Index: 968010 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.6455. Min Act: -0.0000

Data Index: 1089737 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.9446. Min Act: -0.0000

Data Index: 770242 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.6061. Min Act: -0.0000

Data Index: 258354 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8771. Min Act: -0.0000

Data Index: 302090 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 4.1919. Min Range: -4.1919

Max Act: 4.1240. Min Act: -0.0000

Data Index: 689215 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.4743. Min Act: -0.0000

Data Index: 458267 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.6040. Min Act: -0.0000

Data Index: 866095 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.3060. Min Act: -0.0000

Data Index: 964159 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.4703. Min Act: -0.0000

Data Index: 1216203 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.3261. Min Act: -0.0000

Data Index: 1323000 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.2805. Min Act: -0.0000

Data Index: 162152 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.4584. Min Act: -0.0000

Data Index: 472020 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.4278. Min Act: -0.0000

Data Index: 290274 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.4129. Min Act: -0.0000

Data Index: 336196 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.1083. Min Act: -0.0000

Data Index: 508695 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.5477. Min Act: -0.0001

Data Index: 1133080 (C4 (Web Text))

Max Activating Token Index: 211