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

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

Neuron 1941 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2389. Min Act: -0.0000

Data Index: 962548 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2426. Min Act: -0.0000

Data Index: 224946 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2611. Min Act: -0.0001

Data Index: 422550 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2484. Min Act: -0.0000

Data Index: 508520 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2395. Min Act: -0.0000

Data Index: 923052 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2089. Min Act: -0.0000

Data Index: 178042 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1145430 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2120. Min Act: -0.0000

Data Index: 997742 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1901. Min Act: -0.0000

Data Index: 66603 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1931. Min Act: -0.0000

Data Index: 941956 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1951. Min Act: -0.0000

Data Index: 233089 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.2084. Min Act: -0.0001

Data Index: 733477 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1942. Min Act: -0.0000

Data Index: 996879 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1837. Min Act: -0.0000

Data Index: 441818 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1616. Min Act: -0.0000

Data Index: 592977 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1798. Min Act: -0.0000

Data Index: 711602 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1806. Min Act: -0.0000

Data Index: 755121 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1763. Min Act: -0.0001

Data Index: 955186 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1315. Min Act: -0.0000

Data Index: 961556 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.2611. Min Range: -0.2611

Max Act: 0.1522. Min Act: -0.0000

Data Index: 155507 (C4 (Web Text))

Max Activating Token Index: 349