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

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

Neuron 3625 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.5111. Min Act: -0.0001

Data Index: 918508 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4794. Min Act: -0.0001

Data Index: 825194 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4524. Min Act: -0.0001

Data Index: 520437 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4217. Min Act: -0.0001

Data Index: 1129252 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4020. Min Act: -0.0001

Data Index: 254550 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4078. Min Act: -0.0001

Data Index: 350524 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4097. Min Act: -0.0001

Data Index: 1216823 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4066. Min Act: -0.0001

Data Index: 761476 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1290775 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3748. Min Act: -0.0001

Data Index: 762258 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1018089 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3707. Min Act: -0.0001

Data Index: 129508 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3774. Min Act: -0.0001

Data Index: 86958 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1249887 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3879. Min Act: -0.0001

Data Index: 1228033 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3631. Min Act: -0.0001

Data Index: 719384 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3717. Min Act: -0.0001

Data Index: 316075 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3711. Min Act: -0.0001

Data Index: 471855 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1146524 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3598. Min Act: -0.0001

Data Index: 548876 (C4 (Web Text))

Max Activating Token Index: 719