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

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

Neuron 3556 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: 0.5285. Min Range: -0.5285

Max Act: 0.5285. Min Act: -0.0001

Data Index: 148329 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.5248. Min Act: -0.0001

Data Index: 272001 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.5172. Min Act: -0.0000

Data Index: 861818 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4971. Min Act: -0.0001

Data Index: 560634 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4756. Min Act: -0.0001

Data Index: 479129 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4894. Min Act: -0.0000

Data Index: 164524 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1263800 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4705. Min Act: -0.0001

Data Index: 810697 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4773. Min Act: -0.0001

Data Index: 860530 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4728. Min Act: -0.0000

Data Index: 255544 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4708. Min Act: -0.0001

Data Index: 1320778 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4384. Min Act: -0.0001

Data Index: 23371 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4996. Min Act: -0.0001

Data Index: 643971 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4652. Min Act: -0.0001

Data Index: 273380 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4458. Min Act: -0.0000

Data Index: 478149 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4743. Min Act: -0.0000

Data Index: 979497 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4706. Min Act: -0.0000

Data Index: 495337 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4512. Min Act: -0.0000

Data Index: 494526 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4624. Min Act: -0.0001

Data Index: 1114643 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.5285. Min Range: -0.5285

Max Act: 0.4441. Min Act: -0.0001

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 997