Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1542. Min Act: -0.0001

Data Index: 1010229 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1693. Min Act: -0.0001

Data Index: 1232149 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1176. Min Act: -0.0001

Data Index: 520276 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1466. Min Act: -0.0001

Data Index: 12341 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0088. Min Act: -0.0001

Data Index: 260948 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0911. Min Act: -0.0001

Data Index: 107354 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0400. Min Act: -0.0001

Data Index: 77233 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0686. Min Act: -0.0001

Data Index: 644164 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0651. Min Act: -0.0001

Data Index: 147615 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0811. Min Act: -0.0001

Data Index: 815064 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1268097 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0232. Min Act: -0.0001

Data Index: 837081 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0152. Min Act: -0.0001

Data Index: 342853 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0066. Min Act: -0.0001

Data Index: 642316 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9680. Min Act: -0.0001

Data Index: 437861 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9707. Min Act: -0.0001

Data Index: 1064542 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1087223 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9737. Min Act: -0.0001

Data Index: 296592 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9946. Min Act: -0.0001

Data Index: 393512 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0243. Min Act: -0.0001

Data Index: 974968 (C4 (Web Text))

Max Activating Token Index: 982