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

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

Neuron 3814 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5641. Min Range: -2.5641

Max Act: 2.5641. Min Act: -0.0000

Data Index: 45773 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.5778. Min Act: -0.0000

Data Index: 110992 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.5357. Min Act: -0.0000

Data Index: 537411 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.3153. Min Act: 0.0000

Data Index: 589507 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.2889. Min Act: -0.0000

Data Index: 254190 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.2816. Min Act: -0.0000

Data Index: 661785 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.1918. Min Act: -0.0000

Data Index: 588457 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.2753. Min Act: -0.0000

Data Index: 673795 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.2258. Min Act: -0.0000

Data Index: 72465 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1085718 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.1909. Min Act: -0.0000

Data Index: 788301 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.1807. Min Act: 0.0000

Data Index: 307876 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.1682. Min Act: 0.0000

Data Index: 267936 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.2210. Min Act: -0.0000

Data Index: 394929 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.1455. Min Act: -0.0000

Data Index: 377888 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.1052. Min Act: -0.0000

Data Index: 342353 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.0847. Min Act: -0.0000

Data Index: 761830 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.0066. Min Act: -0.0000

Data Index: 925982 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1236558 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 2.5641. Min Range: -2.5641

Max Act: 1.1270. Min Act: -0.0000

Data Index: 766658 (C4 (Web Text))

Max Activating Token Index: 665