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

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

Neuron 918 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1745. Min Range: -2.1745

Max Act: 2.1745. Min Act: -0.0001

Data Index: 402918 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 2.1745. Min Range: -2.1745

Max Act: 2.0331. Min Act: -0.0001

Data Index: 105711 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 2.1745. Min Range: -2.1745

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1058117 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.8077. Min Act: -0.0001

Data Index: 134912 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.6755. Min Act: -0.0001

Data Index: 602815 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1250211 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.6849. Min Act: -0.0001

Data Index: 956981 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.5330. Min Act: -0.0001

Data Index: 745455 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.7267. Min Act: -0.0000

Data Index: 353527 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.6971. Min Act: -0.0001

Data Index: 902161 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.7337. Min Act: -0.0001

Data Index: 824167 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.5488. Min Act: -0.0000

Data Index: 1232350 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.6360. Min Act: -0.0000

Data Index: 804745 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1064109 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1244045 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.5349. Min Act: -0.0000

Data Index: 921759 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.5183. Min Act: -0.0001

Data Index: 563393 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.5271. Min Act: -0.0000

Data Index: 631193 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.5632. Min Act: -0.0000

Data Index: 1256617 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 2.1745. Min Range: -2.1745

Max Act: 1.4680. Min Act: -0.0000

Data Index: 465336 (C4 (Web Text))

Max Activating Token Index: 794