Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5029 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6276. Min Act: -0.0001

Data Index: 167771 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6572. Min Act: -0.0001

Data Index: 717295 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1162072 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5917. Min Act: -0.0001

Data Index: 1246125 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5895. Min Act: -0.0000

Data Index: 806617 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1240592 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6094. Min Act: -0.0001

Data Index: 1305080 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5836. Min Act: -0.0001

Data Index: 1133121 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5670. Min Act: -0.0000

Data Index: 796928 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5194. Min Act: -0.0001

Data Index: 732419 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5353. Min Act: -0.0001

Data Index: 319772 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1043030 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4988. Min Act: -0.0001

Data Index: 442661 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5232. Min Act: -0.0001

Data Index: 1231726 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5114. Min Act: -0.0001

Data Index: 670404 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4716. Min Act: -0.0001

Data Index: 285224 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4955. Min Act: -0.0001

Data Index: 422051 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4616. Min Act: -0.0001

Data Index: 550976 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4882. Min Act: -0.0001

Data Index: 914542 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5140. Min Act: -0.0000

Data Index: 699104 (C4 (Web Text))

Max Activating Token Index: 976