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

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

Neuron 4813 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.3578. Min Act: -0.0000

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9939. Min Act: -0.0000

Data Index: 521188 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1362308 (Python Code)

Max Activating Token Index: 736

Text #3

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9048. Min Act: -0.0000

Data Index: 191020 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9464. Min Act: -0.0000

Data Index: 625505 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9077. Min Act: -0.0000

Data Index: 928317 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9017. Min Act: -0.0000

Data Index: 292076 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1313954 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8288. Min Act: -0.0000

Data Index: 733404 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1213011 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8610. Min Act: -0.0000

Data Index: 626020 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8302. Min Act: -0.0000

Data Index: 926532 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8218. Min Act: -0.0000

Data Index: 286747 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7731. Min Act: -0.0000

Data Index: 620306 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1420013 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8376. Min Act: -0.0000

Data Index: 329362 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8074. Min Act: -0.0000

Data Index: 816495 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8215. Min Act: -0.0000

Data Index: 683952 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8412. Min Act: -0.0000

Data Index: 175087 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1098297 (C4 (Web Text))

Max Activating Token Index: 158