Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4417 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1791. Min Range: -4.1791

Max Act: 4.1791. Min Act: -0.0000

Data Index: 1036887 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 4.1791. Min Range: -4.1791

Max Act: 3.5519. Min Act: -0.0000

Data Index: 930929 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.9697. Min Act: -0.0000

Data Index: 988400 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.7953. Min Act: -0.0000

Data Index: 237974 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.9262. Min Act: -0.0000

Data Index: 629542 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.7604. Min Act: -0.0000

Data Index: 648810 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.8749. Min Act: -0.0000

Data Index: 223912 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.9893. Min Act: -0.0000

Data Index: 93247 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.8664. Min Act: -0.0000

Data Index: 564010 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.9853. Min Act: -0.0000

Data Index: 862090 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.8453. Min Act: -0.0000

Data Index: 405637 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.8213. Min Act: -0.0000

Data Index: 567898 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.6734. Min Act: -0.0000

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.7403. Min Act: -0.0000

Data Index: 1014079 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.6281. Min Act: -0.0000

Data Index: 25176 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.7532. Min Act: -0.0000

Data Index: 1050197 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.7352. Min Act: -0.0000

Data Index: 1208779 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.5932. Min Act: -0.0000

Data Index: 303852 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.7012. Min Act: -0.0000

Data Index: 794848 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 4.1791. Min Range: -4.1791

Max Act: 2.8442. Min Act: -0.0000

Data Index: 932728 (C4 (Web Text))

Max Activating Token Index: 914