Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1050 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.7605. Min Act: -0.0000

Data Index: 1119927 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4435. Min Act: -0.0000

Data Index: 546212 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4628. Min Act: -0.0000

Data Index: 1073432 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.5823. Min Act: -0.0000

Data Index: 1032445 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.7767. Min Act: -0.0000

Data Index: 873199 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3846. Min Act: -0.0000

Data Index: 460625 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3355. Min Act: -0.0000

Data Index: 590901 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4989. Min Act: -0.0000

Data Index: 595629 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4691. Min Act: -0.0000

Data Index: 274137 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3209. Min Act: -0.0000

Data Index: 525015 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4709. Min Act: -0.0000

Data Index: 1120432 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4137. Min Act: -0.0000

Data Index: 1024488 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.5148. Min Act: -0.0000

Data Index: 480375 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4902. Min Act: -0.0000

Data Index: 877553 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.1704. Min Act: -0.0000

Data Index: 1067073 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6125. Min Act: -0.0000

Data Index: 479966 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4789. Min Act: -0.0000

Data Index: 268020 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3046. Min Act: -0.0000

Data Index: 1144833 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.2992. Min Act: -0.0000

Data Index: 152642 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3312. Min Act: -0.0000

Data Index: 560939 (C4 (Web Text))

Max Activating Token Index: 196