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

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

Neuron 294 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.6524. Min Act: -0.0002

Data Index: 1280207 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.2818. Min Act: -0.0001

Data Index: 223900 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.3501. Min Act: -0.0001

Data Index: 250668 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.2283. Min Act: -0.0001

Data Index: 1085274 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.3225. Min Act: -0.0002

Data Index: 553844 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.1745. Min Act: -0.0002

Data Index: 1306112 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.1087. Min Act: -0.0002

Data Index: 137070 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.9100. Min Act: -0.0002

Data Index: 194570 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.0166. Min Act: -0.0002

Data Index: 1208870 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 3.6524. Min Range: -3.6524

Max Act: 3.0086. Min Act: -0.0001

Data Index: 999831 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.5294. Min Act: -0.0002

Data Index: 493604 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.5263. Min Act: -0.0002

Data Index: 53154 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.6383. Min Act: -0.0002

Data Index: 838024 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.5449. Min Act: -0.0001

Data Index: 647371 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.5231. Min Act: -0.0002

Data Index: 358684 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.2368. Min Act: -0.0001

Data Index: 542809 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.2003. Min Act: -0.0001

Data Index: 534598 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.1617. Min Act: -0.0001

Data Index: 1185490 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 3.6524. Min Range: -3.6524

Max Act: 1.9559. Min Act: -0.0001

Data Index: 825401 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.6524. Min Range: -3.6524

Max Act: 2.0636. Min Act: -0.0001

Data Index: 472602 (C4 (Web Text))

Max Activating Token Index: 117