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

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

Neuron 2192 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.4901. Min Range: -12.4901

Max Act: 12.4901. Min Act: -0.0000

Data Index: 909075 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 12.4901. Min Range: -12.4901

Max Act: 12.4018. Min Act: -0.0000

Data Index: 1272638 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 12.4901. Min Range: -12.4901

Max Act: 12.4262. Min Act: -0.0000

Data Index: 64274 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 12.4901. Min Range: -12.4901

Max Act: 12.4641. Min Act: -0.0000

Data Index: 833959 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 12.4901. Min Range: -12.4901

Max Act: 11.8246. Min Act: -0.0000

Data Index: 1232067 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.9328. Min Act: -0.0000

Data Index: 1145626 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 12.4901. Min Range: -12.4901

Max Act: 11.2139. Min Act: -0.0000

Data Index: 554859 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 12.4901. Min Range: -12.4901

Max Act: 11.0780. Min Act: -0.0000

Data Index: 290629 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.9369. Min Act: -0.0000

Data Index: 284745 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.9601. Min Act: -0.0000

Data Index: 713014 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.6986. Min Act: -0.0000

Data Index: 1020981 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.9981. Min Act: -0.0000

Data Index: 1220229 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 12.4901. Min Range: -12.4901

Max Act: 11.1537. Min Act: -0.0000

Data Index: 24893 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 12.4901. Min Range: -12.4901

Max Act: 11.0124. Min Act: -0.0000

Data Index: 1112849 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.7323. Min Act: -0.0000

Data Index: 1107497 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.4074. Min Act: -0.0000

Data Index: 1047272 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.1658. Min Act: -0.0000

Data Index: 916891 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.1957. Min Act: -0.0000

Data Index: 415848 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 12.4901. Min Range: -12.4901

Max Act: 9.7171. Min Act: -0.0000

Data Index: 228902 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 12.4901. Min Range: -12.4901

Max Act: 10.4902. Min Act: -0.0000

Data Index: 493108 (C4 (Web Text))

Max Activating Token Index: 154