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

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

Neuron 3826 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1476. Min Range: -2.1476

Max Act: 2.0756. Min Act: -0.0000

Data Index: 1333757 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.1476. Min Range: -2.1476

Max Act: 2.1476. Min Act: -0.0000

Data Index: 1140599 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 2.1476. Min Range: -2.1476

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1198167 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 2.1476. Min Range: -2.1476

Max Act: 1.2251. Min Act: -0.0000

Data Index: 730570 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 2.1476. Min Range: -2.1476

Max Act: 1.4324. Min Act: -0.0000

Data Index: 515072 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 2.1476. Min Range: -2.1476

Max Act: 1.1071. Min Act: -0.0000

Data Index: 177873 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.1476. Min Range: -2.1476

Max Act: 1.1074. Min Act: -0.0000

Data Index: 164089 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.9834. Min Act: -0.0000

Data Index: 521831 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.8689. Min Act: -0.0000

Data Index: 977815 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 2.1476. Min Range: -2.1476

Max Act: 1.0518. Min Act: -0.0000

Data Index: 499688 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.9218. Min Act: -0.0000

Data Index: 953302 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.7961. Min Act: -0.0000

Data Index: 910338 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.9727. Min Act: -0.0000

Data Index: 416914 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1024434 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1322085 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1219834 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.8673. Min Act: -0.0000

Data Index: 372987 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.6538. Min Act: -0.0000

Data Index: 713162 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1229166 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 2.1476. Min Range: -2.1476

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1485812 (Python Code)

Max Activating Token Index: 909