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

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

Neuron 3633 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0981. Min Range: -3.0981

Max Act: 3.0981. Min Act: -0.0000

Data Index: 1618406 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.9668. Min Act: -0.0000

Data Index: 974506 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.7739. Min Act: -0.0000

Data Index: 28259 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.3977. Min Act: -0.0000

Data Index: 1490800 (Python Code)

Max Activating Token Index: 748

Text #4

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.4571. Min Act: -0.0000

Data Index: 102179 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.3063. Min Act: -0.0000

Data Index: 213390 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.2919. Min Act: -0.0000

Data Index: 1033230 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.1820. Min Act: -0.0000

Data Index: 17232 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.1001. Min Act: -0.0000

Data Index: 780067 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.1012. Min Act: -0.0000

Data Index: 392144 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.0957. Min Act: -0.0000

Data Index: 211711 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.0817. Min Act: -0.0000

Data Index: 33491 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.0466. Min Act: -0.0000

Data Index: 971812 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.0558. Min Act: -0.0000

Data Index: 264568 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.0371. Min Act: -0.0000

Data Index: 820793 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.0147. Min Act: -0.0000

Data Index: 108640 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.0229. Min Act: -0.0000

Data Index: 12522 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.1266. Min Act: -0.0000

Data Index: 302340 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 3.0981. Min Range: -3.0981

Max Act: 1.8792. Min Act: -0.0000

Data Index: 683866 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 3.0981. Min Range: -3.0981

Max Act: 2.1257. Min Act: -0.0000

Data Index: 653837 (C4 (Web Text))

Max Activating Token Index: 445