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

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

Neuron 3277 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1570. Min Act: -0.0001

Data Index: 289939 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9684. Min Act: -0.0001

Data Index: 368033 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1767. Min Act: -0.0001

Data Index: 325474 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0472. Min Act: -0.0001

Data Index: 912103 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0270. Min Act: -0.0001

Data Index: 343214 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0635. Min Act: -0.0001

Data Index: 961742 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1280. Min Act: -0.0001

Data Index: 54069 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9141. Min Act: -0.0001

Data Index: 750306 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0381. Min Act: -0.0001

Data Index: 613944 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.8949. Min Act: -0.0001

Data Index: 39964 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9380. Min Act: -0.0001

Data Index: 185175 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9117. Min Act: -0.0001

Data Index: 1122134 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9528. Min Act: -0.0001

Data Index: 88207 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9116. Min Act: -0.0001

Data Index: 390132 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0307. Min Act: -0.0001

Data Index: 1051251 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1017053 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.8382. Min Act: -0.0001

Data Index: 379175 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.8895. Min Act: -0.0001

Data Index: 438260 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9058. Min Act: -0.0001

Data Index: 420178 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.8213. Min Act: -0.0001

Data Index: 1195052 (C4 (Web Text))

Max Activating Token Index: 888