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

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

Neuron 3536 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: 2.3453. Min Range: -2.3453

Max Act: 2.3453. Min Act: -0.0000

Data Index: 697619 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.7853. Min Act: -0.0000

Data Index: 705314 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.8096. Min Act: -0.0000

Data Index: 40864 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1273956 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.3156. Min Act: -0.0000

Data Index: 896071 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.4455. Min Act: -0.0000

Data Index: 506229 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.2397. Min Act: -0.0000

Data Index: 956036 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1101253 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.3146. Min Act: -0.0000

Data Index: 698658 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.2283. Min Act: -0.0000

Data Index: 70704 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.1858. Min Act: -0.0000

Data Index: 714479 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.1898. Min Act: -0.0000

Data Index: 400547 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.1414. Min Act: -0.0000

Data Index: 250806 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.0672. Min Act: -0.0000

Data Index: 284847 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.1062. Min Act: -0.0000

Data Index: 480938 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.0385. Min Act: -0.0000

Data Index: 923965 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.0887. Min Act: -0.0000

Data Index: 402924 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1270203 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1293061 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 2.3453. Min Range: -2.3453

Max Act: 1.0010. Min Act: -0.0000

Data Index: 635451 (C4 (Web Text))

Max Activating Token Index: 215