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

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

Neuron 1994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2816. Min Range: -2.2816

Max Act: 2.2816. Min Act: -0.0000

Data Index: 879865 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 2.2816. Min Range: -2.2816

Max Act: 2.1893. Min Act: -0.0000

Data Index: 1079338 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 2.2816. Min Range: -2.2816

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1233227 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.9948. Min Act: -0.0000

Data Index: 436962 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 2.2816. Min Range: -2.2816

Max Act: 2.2259. Min Act: -0.0000

Data Index: 850468 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.8597. Min Act: -0.0000

Data Index: 700567 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7896. Min Act: -0.0000

Data Index: 450273 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7197. Min Act: -0.0000

Data Index: 1151894 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7803. Min Act: -0.0000

Data Index: 847798 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.9275. Min Act: -0.0000

Data Index: 843927 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7813. Min Act: -0.0000

Data Index: 110116 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7141. Min Act: -0.0000

Data Index: 419968 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7026. Min Act: -0.0000

Data Index: 223200 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7589. Min Act: -0.0000

Data Index: 364328 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.6388. Min Act: -0.0000

Data Index: 838017 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1150104 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.6289. Min Act: -0.0000

Data Index: 1130457 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.6132. Min Act: -0.0000

Data Index: 775760 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1309655 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 2.2816. Min Range: -2.2816

Max Act: 1.7003. Min Act: -0.0000

Data Index: 60326 (C4 (Web Text))

Max Activating Token Index: 695