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

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

Neuron 1835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2633. Min Act: -0.0000

Data Index: 440637 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2490. Min Act: -0.0000

Data Index: 606279 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2392. Min Act: -0.0000

Data Index: 963156 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2315. Min Act: -0.0000

Data Index: 58127 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1209724 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1248405 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2117. Min Act: -0.0000

Data Index: 929560 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1232308 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2036. Min Act: -0.0000

Data Index: 924243 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2248. Min Act: -0.0000

Data Index: 590724 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2012. Min Act: -0.0000

Data Index: 245958 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2070. Min Act: -0.0000

Data Index: 276782 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1309518 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2114. Min Act: -0.0000

Data Index: 908075 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.1954. Min Act: -0.0000

Data Index: 173416 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2099. Min Act: -0.0000

Data Index: 163438 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.2092. Min Act: -0.0000

Data Index: 818985 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.1930. Min Act: -0.0000

Data Index: 203149 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.1980. Min Act: -0.0000

Data Index: 900984 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.2633. Min Range: -0.2633

Max Act: 0.1911. Min Act: -0.0000

Data Index: 452182 (C4 (Web Text))

Max Activating Token Index: 54