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

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

Neuron 1542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.9492. Min Act: -0.0001

Data Index: 455877 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.9270. Min Act: -0.0001

Data Index: 770315 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.8714. Min Act: -0.0001

Data Index: 1170338 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.8262. Min Act: -0.0001

Data Index: 156143 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.7689. Min Act: -0.0000

Data Index: 483863 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6984. Min Act: -0.0001

Data Index: 1008977 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.7137. Min Act: -0.0001

Data Index: 465904 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6602. Min Act: -0.0001

Data Index: 670700 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.7232. Min Act: -0.0001

Data Index: 1065458 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6517. Min Act: -0.0001

Data Index: 646759 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6937. Min Act: -0.0000

Data Index: 580164 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6501. Min Act: -0.0000

Data Index: 276025 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6113. Min Act: -0.0001

Data Index: 241511 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6425. Min Act: -0.0001

Data Index: 807184 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1155836 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.5711. Min Act: -0.0001

Data Index: 279940 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6279. Min Act: -0.0001

Data Index: 157157 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.6151. Min Act: -0.0001

Data Index: 466712 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.5992. Min Act: -0.0001

Data Index: 1135921 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.9492. Min Range: -0.9492

Max Act: 0.5579. Min Act: -0.0000

Data Index: 300446 (C4 (Web Text))

Max Activating Token Index: 455