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

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

Neuron 2975 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: 1.1468. Min Range: -1.1468

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1257876 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0858. Min Act: -0.0000

Data Index: 951660 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1011841 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0825. Min Act: -0.0000

Data Index: 998889 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1273470 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8933. Min Act: -0.0000

Data Index: 264425 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8069. Min Act: -0.0000

Data Index: 644501 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9222. Min Act: -0.0000

Data Index: 826450 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8785. Min Act: -0.0000

Data Index: 512154 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1394961 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1377403 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8256. Min Act: -0.0000

Data Index: 367994 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1076003 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1635749 (Python Code)

Max Activating Token Index: 704

Text #14

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1519037 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1508390 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8166. Min Act: -0.0000

Data Index: 389652 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1426326 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1638699 (Python Code)

Max Activating Token Index: 857

Text #19

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1635992 (Python Code)

Max Activating Token Index: 619