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

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

Neuron 5322 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: 0.5167. Min Range: -0.5167

Max Act: 0.5167. Min Act: 0.0000

Data Index: 484405 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4365. Min Act: -0.0000

Data Index: 690448 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4203. Min Act: -0.0000

Data Index: 365700 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3898. Min Act: -0.0000

Data Index: 324119 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3863. Min Act: -0.0000

Data Index: 824920 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3615. Min Act: -0.0000

Data Index: 475905 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3493. Min Act: -0.0000

Data Index: 462682 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3683. Min Act: -0.0000

Data Index: 776593 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3413. Min Act: -0.0000

Data Index: 775302 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1075889 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1077926 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1256102 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3258. Min Act: -0.0000

Data Index: 679189 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3283. Min Act: -0.0000

Data Index: 496407 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1252839 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1059235 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1084714 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.2961. Min Act: -0.0000

Data Index: 125544 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3155. Min Act: -0.0000

Data Index: 613952 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.2904. Min Act: -0.0000

Data Index: 849396 (C4 (Web Text))

Max Activating Token Index: 56