Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1575 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.3016. Min Act: -0.0001

Data Index: 616784 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1119. Min Act: -0.0001

Data Index: 367841 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0431. Min Act: -0.0001

Data Index: 835468 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9194. Min Act: -0.0001

Data Index: 23978 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0270. Min Act: -0.0001

Data Index: 979017 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9286. Min Act: -0.0001

Data Index: 554646 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8823. Min Act: -0.0001

Data Index: 310349 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9354. Min Act: -0.0001

Data Index: 926607 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9165. Min Act: -0.0001

Data Index: 1301080 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9396. Min Act: -0.0001

Data Index: 1172670 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9333. Min Act: -0.0001

Data Index: 1097731 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9117. Min Act: -0.0001

Data Index: 1336056 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9300. Min Act: -0.0001

Data Index: 51639 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9278. Min Act: -0.0001

Data Index: 1230935 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8628. Min Act: -0.0001

Data Index: 712148 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1315972 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7673. Min Act: -0.0001

Data Index: 453022 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8681. Min Act: -0.0001

Data Index: 1175336 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8340. Min Act: -0.0001

Data Index: 620457 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8537. Min Act: -0.0000

Data Index: 702535 (C4 (Web Text))

Max Activating Token Index: 619