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

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

Neuron 3704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.3292. Min Act: -0.0000

Data Index: 24316 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.6224. Min Act: -0.0000

Data Index: 1141581 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.7530. Min Act: -0.0000

Data Index: 885067 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.7401. Min Act: -0.0000

Data Index: 74201 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.7383. Min Act: -0.0000

Data Index: 1492783 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.7018. Min Act: -0.0000

Data Index: 888067 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.6355. Min Act: -0.0000

Data Index: 97894 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.5804. Min Act: -0.0000

Data Index: 1307025 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.4704. Min Act: -0.0000

Data Index: 1380790 (Python Code)

Max Activating Token Index: 725

Text #9

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.5785. Min Act: -0.0000

Data Index: 889360 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.4552. Min Act: -0.0000

Data Index: 27687 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.5685. Min Act: -0.0000

Data Index: 679965 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.6599. Min Act: -0.0000

Data Index: 855568 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.4783. Min Act: -0.0000

Data Index: 1119260 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.3420. Min Act: -0.0000

Data Index: 873878 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.4736. Min Act: -0.0000

Data Index: 782970 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.4416. Min Act: -0.0000

Data Index: 606440 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.5305. Min Act: -0.0000

Data Index: 217522 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.5532. Min Act: -0.0000

Data Index: 444496 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 3.3292. Min Range: -3.3292

Max Act: 2.4169. Min Act: -0.0000

Data Index: 1314547 (C4 (Web Text))

Max Activating Token Index: 678