Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 245 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0686. Min Act: -0.0005

Data Index: 629877 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0656. Min Act: -0.0005

Data Index: 450212 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0678. Min Act: -0.0005

Data Index: 1357258 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0005

Data Index: 592222 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0005

Data Index: 1291092 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0662. Min Act: -0.0005

Data Index: 1355616 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0660. Min Act: -0.0005

Data Index: 502527 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0672. Min Act: -0.0005

Data Index: 959795 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0645. Min Act: -0.0005

Data Index: 1190167 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0657. Min Act: -0.0005

Data Index: 758484 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0641. Min Act: -0.0005

Data Index: 1153187 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0655. Min Act: -0.0005

Data Index: 1030745 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0636. Min Act: -0.0005

Data Index: 696159 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0650. Min Act: -0.0005

Data Index: 1089290 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0615. Min Act: -0.0005

Data Index: 1180680 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0643. Min Act: -0.0005

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0610. Min Act: -0.0005

Data Index: 776515 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0655. Min Act: -0.0005

Data Index: 1273712 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0642. Min Act: -0.0005

Data Index: 516946 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0641. Min Act: -0.0005

Data Index: 954121 (C4 (Web Text))

Max Activating Token Index: 251