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

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

Neuron 2243 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: 0.9734. Min Range: -0.9734

Max Act: 0.9734. Min Act: -0.0001

Data Index: 897903 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7956. Min Act: -0.0001

Data Index: 449591 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8053. Min Act: -0.0001

Data Index: 1135273 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8403. Min Act: -0.0001

Data Index: 57054 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7610. Min Act: -0.0001

Data Index: 530514 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7995. Min Act: -0.0001

Data Index: 253233 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7444. Min Act: -0.0001

Data Index: 415782 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1113946 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7846. Min Act: -0.0001

Data Index: 1281154 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7854. Min Act: -0.0001

Data Index: 99850 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7703. Min Act: -0.0001

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7615. Min Act: -0.0001

Data Index: 33217 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7699. Min Act: -0.0001

Data Index: 792501 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7626. Min Act: -0.0001

Data Index: 363139 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7110. Min Act: -0.0001

Data Index: 791944 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7307. Min Act: -0.0001

Data Index: 685004 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7024. Min Act: -0.0001

Data Index: 920733 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6877. Min Act: -0.0001

Data Index: 753329 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6696. Min Act: -0.0001

Data Index: 634710 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6704. Min Act: -0.0001

Data Index: 461037 (C4 (Web Text))

Max Activating Token Index: 585