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

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

Neuron 4923 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0006. Min Range: -2.0006

Max Act: 2.0006. Min Act: -0.0000

Data Index: 663494 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.0006. Min Range: -2.0006

Max Act: 1.3715. Min Act: -0.0000

Data Index: 508962 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 2.0006. Min Range: -2.0006

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1342443 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 2.0006. Min Range: -2.0006

Max Act: 1.2374. Min Act: -0.0000

Data Index: 469799 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 2.0006. Min Range: -2.0006

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1144906 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 2.0006. Min Range: -2.0006

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1176779 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 2.0006. Min Range: -2.0006

Max Act: 1.1750. Min Act: -0.0000

Data Index: 455020 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.9332. Min Act: -0.0000

Data Index: 408761 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.9435. Min Act: -0.0000

Data Index: 255104 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.9261. Min Act: -0.0000

Data Index: 233112 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1153469 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.9350. Min Act: -0.0000

Data Index: 829737 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.9248. Min Act: -0.0000

Data Index: 166896 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.8473. Min Act: -0.0000

Data Index: 629812 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.9900. Min Act: -0.0000

Data Index: 286851 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1096145 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1041885 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.8032. Min Act: -0.0000

Data Index: 707058 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1247453 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 2.0006. Min Range: -2.0006

Max Act: 0.8392. Min Act: -0.0000

Data Index: 343101 (C4 (Web Text))

Max Activating Token Index: 584