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

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

Neuron 5860 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: 6.9063. Min Range: -6.9063

Max Act: 6.9063. Min Act: -0.0000

Data Index: 1091777 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.7229. Min Act: -0.0000

Data Index: 1313675 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.3536. Min Act: -0.0000

Data Index: 80159 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.3202. Min Act: -0.0000

Data Index: 461163 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.8265. Min Act: -0.0000

Data Index: 623856 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.3534. Min Act: -0.0000

Data Index: 1054478 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.3050. Min Act: -0.0000

Data Index: 1201817 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.4681. Min Act: -0.0000

Data Index: 424220 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.2187. Min Act: -0.0000

Data Index: 565235 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.3482. Min Act: -0.0000

Data Index: 1339658 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.1056. Min Act: -0.0000

Data Index: 623041 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.8451. Min Act: -0.0000

Data Index: 1158510 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.9890. Min Act: -0.0000

Data Index: 1316432 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.9579. Min Act: -0.0000

Data Index: 536700 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.5825. Min Act: -0.0000

Data Index: 795853 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.9597. Min Act: -0.0000

Data Index: 214623 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.5337. Min Act: -0.0000

Data Index: 1281781 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.5040. Min Act: -0.0000

Data Index: 579084 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.6625. Min Act: -0.0000

Data Index: 1296889 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.8416. Min Act: -0.0000

Data Index: 66419 (C4 (Web Text))

Max Activating Token Index: 418