Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1841 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2704. Min Range: -3.2704

Max Act: 3.2704. Min Act: -0.0000

Data Index: 782633 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.9071. Min Act: -0.0000

Data Index: 1295990 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.9565. Min Act: -0.0000

Data Index: 118364 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.9506. Min Act: -0.0000

Data Index: 29584 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.9509. Min Act: -0.0000

Data Index: 775449 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.8939. Min Act: -0.0000

Data Index: 980491 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.7316. Min Act: -0.0000

Data Index: 857567 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.7559. Min Act: -0.0000

Data Index: 207963 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.6136. Min Act: -0.0000

Data Index: 448130 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.7197. Min Act: -0.0000

Data Index: 1153033 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.8347. Min Act: -0.0000

Data Index: 180395 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.8162. Min Act: -0.0000

Data Index: 1299389 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.9526. Min Act: -0.0000

Data Index: 12250 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.5512. Min Act: -0.0000

Data Index: 978200 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.6567. Min Act: -0.0000

Data Index: 709999 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.7703. Min Act: -0.0000

Data Index: 411723 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.7267. Min Act: -0.0000

Data Index: 691909 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.6068. Min Act: -0.0000

Data Index: 334622 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.5202. Min Act: -0.0000

Data Index: 560401 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 3.2704. Min Range: -3.2704

Max Act: 2.6019. Min Act: -0.0000

Data Index: 566190 (C4 (Web Text))

Max Activating Token Index: 802