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

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

Neuron 5668 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.2882. Min Act: -0.0001

Data Index: 1013886 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0795. Min Act: -0.0001

Data Index: 642988 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1065760 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0386. Min Act: -0.0000

Data Index: 981711 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1073772 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1058. Min Act: -0.0000

Data Index: 821705 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1320. Min Act: -0.0000

Data Index: 544971 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0329. Min Act: -0.0001

Data Index: 582048 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1940. Min Act: -0.0001

Data Index: 1252392 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0515. Min Act: -0.0000

Data Index: 956818 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0336. Min Act: -0.0001

Data Index: 1102001 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0532. Min Act: -0.0001

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0501. Min Act: -0.0001

Data Index: 1349147 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1303869 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9583. Min Act: -0.0001

Data Index: 861919 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0173. Min Act: -0.0001

Data Index: 1291198 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9690. Min Act: -0.0001

Data Index: 847338 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9700. Min Act: -0.0001

Data Index: 709115 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9970. Min Act: -0.0001

Data Index: 996611 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1072332 (C4 (Web Text))

Max Activating Token Index: 38