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

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

Neuron 3236 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: 1.5347. Min Range: -1.5347

Max Act: 1.5347. Min Act: -0.0001

Data Index: 882114 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2328. Min Act: -0.0001

Data Index: 949889 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.4231. Min Act: -0.0001

Data Index: 33920 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2586. Min Act: -0.0001

Data Index: 1157262 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.3840. Min Act: -0.0001

Data Index: 634409 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1776. Min Act: -0.0001

Data Index: 656406 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2109. Min Act: -0.0001

Data Index: 1498125 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2736. Min Act: -0.0001

Data Index: 585007 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2092. Min Act: -0.0001

Data Index: 550760 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.3879. Min Act: -0.0001

Data Index: 755248 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1783. Min Act: -0.0001

Data Index: 1047827 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1155. Min Act: -0.0001

Data Index: 809106 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1676. Min Act: -0.0001

Data Index: 1332704 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2934. Min Act: -0.0001

Data Index: 1130016 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1470. Min Act: -0.0001

Data Index: 836849 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1447. Min Act: -0.0001

Data Index: 56376 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1123. Min Act: -0.0001

Data Index: 73401 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2597. Min Act: -0.0001

Data Index: 934038 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0630. Min Act: -0.0001

Data Index: 135370 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1185. Min Act: -0.0001

Data Index: 510576 (C4 (Web Text))

Max Activating Token Index: 814