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

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

Neuron 894 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: 1.5173. Min Range: -1.5173

Max Act: 1.5173. Min Act: -0.0001

Data Index: 1128727 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.3654. Min Act: -0.0001

Data Index: 361749 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1418. Min Act: -0.0001

Data Index: 368073 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.3499. Min Act: -0.0001

Data Index: 265315 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.2789. Min Act: -0.0001

Data Index: 927587 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.2100. Min Act: -0.0001

Data Index: 124329 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1779. Min Act: -0.0001

Data Index: 847600 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.2684. Min Act: -0.0001

Data Index: 296211 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1650. Min Act: -0.0001

Data Index: 4331 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1917. Min Act: -0.0001

Data Index: 753981 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1038. Min Act: -0.0001

Data Index: 719801 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1743. Min Act: -0.0001

Data Index: 1042171 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1121. Min Act: -0.0001

Data Index: 260413 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1303. Min Act: -0.0001

Data Index: 145244 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.0065. Min Act: -0.0001

Data Index: 1265237 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1487. Min Act: -0.0001

Data Index: 321110 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1086. Min Act: -0.0001

Data Index: 1291773 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1257. Min Act: -0.0001

Data Index: 1275514 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1837. Min Act: -0.0001

Data Index: 1184154 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.0439. Min Act: -0.0001

Data Index: 312001 (C4 (Web Text))

Max Activating Token Index: 180