Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1826 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3506. Min Act: -0.0003

Data Index: 1242613 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3650. Min Act: -0.0003

Data Index: 491248 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3186. Min Act: -0.0003

Data Index: 902526 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3142. Min Act: -0.0003

Data Index: 1164830 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3183. Min Act: -0.0003

Data Index: 1237142 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3080. Min Act: -0.0003

Data Index: 1232274 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2995. Min Act: -0.0003

Data Index: 911654 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2977. Min Act: -0.0003

Data Index: 190713 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2989. Min Act: -0.0004

Data Index: 328347 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2812. Min Act: -0.0003

Data Index: 691247 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2861. Min Act: -0.0002

Data Index: 77910 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2731. Min Act: -0.0003

Data Index: 962129 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2916. Min Act: -0.0003

Data Index: 1297017 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2673. Min Act: -0.0004

Data Index: 187543 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2779. Min Act: -0.0003

Data Index: 997018 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2744. Min Act: -0.0003

Data Index: 71099 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2587. Min Act: -0.0003

Data Index: 1299185 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2777. Min Act: -0.0003

Data Index: 472517 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2751. Min Act: -0.0003

Data Index: 226220 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2795. Min Act: -0.0003

Data Index: 32080 (C4 (Web Text))

Max Activating Token Index: 212