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

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

Neuron 4128 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.4945. Min Act: -0.0000

Data Index: 972100 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.7278. Min Act: -0.0000

Data Index: 691362 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.2297. Min Act: -0.0000

Data Index: 206187 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.2189. Min Act: -0.0000

Data Index: 452052 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.1342. Min Act: -0.0000

Data Index: 953928 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.0103. Min Act: -0.0000

Data Index: 225110 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.1620. Min Act: -0.0000

Data Index: 1003878 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.9337. Min Act: -0.0000

Data Index: 358238 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 2.7278. Min Range: -2.7278

Max Act: 2.0014. Min Act: -0.0000

Data Index: 1340740 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.8719. Min Act: -0.0000

Data Index: 602140 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.9063. Min Act: -0.0000

Data Index: 352978 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.7917. Min Act: -0.0000

Data Index: 786244 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.7793. Min Act: 0.0000

Data Index: 1170484 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.6828. Min Act: -0.0000

Data Index: 395318 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1233515 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.6080. Min Act: -0.0000

Data Index: 1206679 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.5763. Min Act: -0.0000

Data Index: 383993 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.5370. Min Act: -0.0000

Data Index: 677102 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1327004 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 2.7278. Min Range: -2.7278

Max Act: 1.5426. Min Act: -0.0000

Data Index: 294903 (C4 (Web Text))

Max Activating Token Index: 131