Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3291 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.5524. Min Act: -0.0001

Data Index: 681566 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.4285. Min Act: -0.0001

Data Index: 1245443 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.4220. Min Act: -0.0001

Data Index: 998107 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.3653. Min Act: -0.0001

Data Index: 869209 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.3716. Min Act: -0.0001

Data Index: 378762 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.3455. Min Act: -0.0001

Data Index: 339358 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.4043. Min Act: -0.0001

Data Index: 1082029 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.3609. Min Act: -0.0001

Data Index: 341608 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2959. Min Act: -0.0001

Data Index: 1323126 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.3409. Min Act: -0.0001

Data Index: 451384 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.3237. Min Act: -0.0001

Data Index: 1276289 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2384. Min Act: -0.0001

Data Index: 960964 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1766. Min Act: -0.0001

Data Index: 45939 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1573. Min Act: -0.0001

Data Index: 14806 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2226. Min Act: -0.0001

Data Index: 456708 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0808. Min Act: -0.0001

Data Index: 88423 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0178. Min Act: -0.0001

Data Index: 443332 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0435. Min Act: -0.0001

Data Index: 311561 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0571. Min Act: -0.0001

Data Index: 154824 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0885. Min Act: -0.0001

Data Index: 647805 (C4 (Web Text))

Max Activating Token Index: 705