Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 841 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2300. Min Act: -0.0003

Data Index: 1026942 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2230. Min Act: -0.0003

Data Index: 447514 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2193. Min Act: -0.0003

Data Index: 334535 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2070. Min Act: -0.0003

Data Index: 278657 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2034. Min Act: -0.0003

Data Index: 984784 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.2029. Min Act: -0.0003

Data Index: 590719 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1967. Min Act: -0.0003

Data Index: 770728 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1872. Min Act: -0.0004

Data Index: 1070129 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1944. Min Act: -0.0004

Data Index: 359884 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1783. Min Act: -0.0003

Data Index: 1187283 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1846. Min Act: -0.0003

Data Index: 355663 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1755. Min Act: -0.0003

Data Index: 757115 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1861. Min Act: -0.0003

Data Index: 1212427 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1834. Min Act: -0.0003

Data Index: 489812 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1834. Min Act: -0.0004

Data Index: 447033 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1699. Min Act: -0.0003

Data Index: 595650 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1665. Min Act: -0.0003

Data Index: 1135587 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1799. Min Act: -0.0003

Data Index: 1312979 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1717. Min Act: -0.0003

Data Index: 646702 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1614. Min Act: -0.0003

Data Index: 888457 (C4 (Web Text))

Max Activating Token Index: 887