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

Dataset: The Pile

Neuron 3642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4726. Min Range: -5.4726

Max Act: 5.4726. Min Act: -0.0000

Data Index: 368186 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 5.4726. Min Range: -5.4726

Max Act: 5.0659. Min Act: -0.0000

Data Index: 161552 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1164. Min Act: -0.0000

Data Index: 1903899 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.2728. Min Act: -0.0000

Data Index: 1236843 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.0819. Min Act: -0.0000

Data Index: 966669 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.9180. Min Act: -0.0000

Data Index: 320590 (The Pile)

Max Activating Token Index: 681

Text #6

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.9090. Min Act: -0.0000

Data Index: 1777224 (The Pile)

Max Activating Token Index: 366

Text #7

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.0436. Min Act: -0.0000

Data Index: 37980 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1908. Min Act: -0.0000

Data Index: 1559110 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1267. Min Act: -0.0000

Data Index: 1919724 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1669. Min Act: -0.0000

Data Index: 1451362 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 5.4726. Min Range: -5.4726

Max Act: 4.1082. Min Act: -0.0000

Data Index: 486258 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.9243. Min Act: -0.0000

Data Index: 1878666 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.8606. Min Act: -0.0000

Data Index: 699517 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.8529. Min Act: -0.0000

Data Index: 605968 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.8012. Min Act: -0.0000

Data Index: 208591 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.6111. Min Act: -0.0000

Data Index: 1833503 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.8873. Min Act: -0.0000

Data Index: 602653 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.7432. Min Act: -0.0000

Data Index: 1834205 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 5.4726. Min Range: -5.4726

Max Act: 3.4003. Min Act: -0.0000

Data Index: 1291531 (The Pile)

Max Activating Token Index: 668