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

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

Neuron 2084 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0823. Min Range: -1.0823

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1094700 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.8641. Min Act: -0.0000

Data Index: 960469 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.0823. Min Range: -1.0823

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1216207 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.9199. Min Act: -0.0000

Data Index: 749448 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.9138. Min Act: -0.0000

Data Index: 833537 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1081647 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.9530. Min Act: -0.0000

Data Index: 527874 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.9244. Min Act: -0.0000

Data Index: 678614 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.8520. Min Act: -0.0000

Data Index: 951048 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.9083. Min Act: -0.0000

Data Index: 118711 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.8814. Min Act: -0.0000

Data Index: 599435 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1339453 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.7982. Min Act: -0.0000

Data Index: 48151 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.8424. Min Act: -0.0000

Data Index: 762060 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.7715. Min Act: -0.0000

Data Index: 669937 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.7863. Min Act: -0.0000

Data Index: 893283 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.7870. Min Act: -0.0000

Data Index: 558649 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1028263 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.7759. Min Act: -0.0000

Data Index: 95115 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.0823. Min Range: -1.0823

Max Act: 0.7807. Min Act: -0.0000

Data Index: 321111 (C4 (Web Text))

Max Activating Token Index: 377