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

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

Neuron 1994 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.6412. Min Act: -0.0000

Data Index: 1488058 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.4330. Min Act: -0.0000

Data Index: 371903 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1643964 (Python Code)

Max Activating Token Index: 757

Text #3

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.0811. Min Act: -0.0000

Data Index: 828086 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.1521. Min Act: -0.0000

Data Index: 758810 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.2886. Min Act: -0.0000

Data Index: 2998 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.2339. Min Act: -0.0000

Data Index: 405544 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.6412. Min Range: -1.6412

Max Act: 0.9777. Min Act: -0.0000

Data Index: 535329 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.1383. Min Act: -0.0000

Data Index: 860431 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1556740 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.0327. Min Act: -0.0000

Data Index: 552722 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1409905 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 1.6412. Min Range: -1.6412

Max Act: 0.9808. Min Act: -0.0000

Data Index: 56957 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1488847 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1581897 (Python Code)

Max Activating Token Index: 713

Text #16

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.0222. Min Act: -0.0000

Data Index: 9274 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1345916 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.6412. Min Range: -1.6412

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1337969 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.6412. Min Range: -1.6412

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1255853 (C4 (Web Text))

Max Activating Token Index: 76