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

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

Neuron 1208 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: 3.5780. Min Range: -3.5780

Max Act: 3.5780. Min Act: -0.0000

Data Index: 1402194 (Python Code)

Max Activating Token Index: 357

Text #1

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.9560. Min Act: -0.0000

Data Index: 558417 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.9731. Min Act: -0.0001

Data Index: 388306 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.4738. Min Act: -0.0000

Data Index: 130288 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.7167. Min Act: -0.0000

Data Index: 604245 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.7184. Min Act: -0.0000

Data Index: 1286193 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.6818. Min Act: -0.0000

Data Index: 968036 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.6171. Min Act: -0.0000

Data Index: 1336182 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.4797. Min Act: -0.0000

Data Index: 447298 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.5688. Min Act: -0.0001

Data Index: 20774 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.6011. Min Act: -0.0001

Data Index: 1326087 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.4655. Min Act: -0.0000

Data Index: 1240685 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.3169. Min Act: -0.0000

Data Index: 872080 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.5456. Min Act: -0.0000

Data Index: 629924 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.5132. Min Act: -0.0000

Data Index: 934568 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.5288. Min Act: -0.0000

Data Index: 870939 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.2642. Min Act: -0.0000

Data Index: 884343 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.4969. Min Act: -0.0000

Data Index: 1351887 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.4654. Min Act: -0.0001

Data Index: 542328 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.5765. Min Act: -0.0000

Data Index: 14095 (C4 (Web Text))

Max Activating Token Index: 103