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

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

Neuron 680 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: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0005

Data Index: 1332829 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0827. Min Act: -0.0005

Data Index: 975115 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0773. Min Act: -0.0005

Data Index: 1156543 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0818. Min Act: -0.0005

Data Index: 369991 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0778. Min Act: -0.0005

Data Index: 1152985 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0779. Min Act: -0.0005

Data Index: 566240 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0770. Min Act: -0.0005

Data Index: 11999 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0732. Min Act: -0.0005

Data Index: 672705 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0721. Min Act: -0.0005

Data Index: 286803 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0761. Min Act: -0.0005

Data Index: 366847 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0731. Min Act: -0.0005

Data Index: 784085 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0680. Min Act: -0.0005

Data Index: 500713 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0686. Min Act: -0.0005

Data Index: 966707 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0662. Min Act: -0.0005

Data Index: 536781 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0713. Min Act: -0.0005

Data Index: 118023 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0709. Min Act: -0.0005

Data Index: 64614 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0691. Min Act: -0.0005

Data Index: 255058 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0688. Min Act: -0.0005

Data Index: 477929 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0709. Min Act: -0.0005

Data Index: 463456 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0670. Min Act: -0.0005

Data Index: 1244131 (C4 (Web Text))

Max Activating Token Index: 242