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

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

Neuron 146 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: 1.4067. Min Range: -1.4067

Max Act: 1.4067. Min Act: -0.0001

Data Index: 269454 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.4050. Min Act: -0.0001

Data Index: 1297616 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.2694. Min Act: -0.0001

Data Index: 508241 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.3981. Min Act: -0.0001

Data Index: 41219 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.2876. Min Act: -0.0000

Data Index: 441353 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.2263. Min Act: -0.0001

Data Index: 1279219 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1997. Min Act: -0.0001

Data Index: 1121463 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1365. Min Act: -0.0001

Data Index: 659842 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1742. Min Act: -0.0000

Data Index: 9303 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1744. Min Act: -0.0001

Data Index: 259888 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0873. Min Act: -0.0001

Data Index: 1314596 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0593. Min Act: -0.0001

Data Index: 8670 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0836. Min Act: -0.0001

Data Index: 1084038 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0192. Min Act: -0.0001

Data Index: 825616 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1275. Min Act: -0.0001

Data Index: 904173 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0631. Min Act: -0.0001

Data Index: 127189 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0592. Min Act: -0.0001

Data Index: 497063 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0576. Min Act: -0.0001

Data Index: 245651 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0541. Min Act: -0.0001

Data Index: 449903 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9952. Min Act: -0.0000

Data Index: 750860 (C4 (Web Text))

Max Activating Token Index: 14