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

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

Neuron 2809 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: 3.4921. Min Range: -3.4921

Max Act: 3.4921. Min Act: -0.0000

Data Index: 549512 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.2171. Min Act: -0.0000

Data Index: 84241 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9199. Min Act: -0.0000

Data Index: 731073 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.0323. Min Act: -0.0000

Data Index: 48251 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9254. Min Act: -0.0000

Data Index: 416271 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.8162. Min Act: -0.0000

Data Index: 593336 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.8968. Min Act: -0.0000

Data Index: 612885 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.7649. Min Act: -0.0000

Data Index: 730863 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.7297. Min Act: -0.0000

Data Index: 1351873 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.8259. Min Act: -0.0000

Data Index: 1052440 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.6616. Min Act: -0.0000

Data Index: 186770 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.8103. Min Act: -0.0000

Data Index: 375985 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.6187. Min Act: -0.0000

Data Index: 676647 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.8988. Min Act: -0.0000

Data Index: 609479 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.8765. Min Act: -0.0000

Data Index: 82624 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.6853. Min Act: -0.0000

Data Index: 1292390 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.6710. Min Act: -0.0000

Data Index: 92864 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.6261. Min Act: -0.0000

Data Index: 349415 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.7448. Min Act: -0.0000

Data Index: 327806 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.4730. Min Act: -0.0000

Data Index: 776846 (C4 (Web Text))

Max Activating Token Index: 470