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

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

Neuron 2248 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: 5.2756. Min Range: -5.2756

Max Act: 5.2756. Min Act: -0.0001

Data Index: 480112 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 5.2756. Min Range: -5.2756

Max Act: 4.5613. Min Act: -0.0001

Data Index: 591047 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 5.2756. Min Range: -5.2756

Max Act: 4.8050. Min Act: -0.0001

Data Index: 329657 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 5.2756. Min Range: -5.2756

Max Act: 4.8191. Min Act: -0.0001

Data Index: 577596 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 5.2756. Min Range: -5.2756

Max Act: 4.1386. Min Act: -0.0001

Data Index: 325488 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 5.2756. Min Range: -5.2756

Max Act: 4.2019. Min Act: -0.0001

Data Index: 632449 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 5.2756. Min Range: -5.2756

Max Act: 4.3735. Min Act: -0.0001

Data Index: 1267857 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.9037. Min Act: -0.0001

Data Index: 38479 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 5.2756. Min Range: -5.2756

Max Act: 4.0568. Min Act: -0.0001

Data Index: 693949 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.8252. Min Act: -0.0001

Data Index: 443923 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.2154. Min Act: -0.0001

Data Index: 742665 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.8511. Min Act: -0.0001

Data Index: 1115004 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.5276. Min Act: -0.0001

Data Index: 66984 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.5860. Min Act: -0.0001

Data Index: 1349358 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.3776. Min Act: -0.0001

Data Index: 253677 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.5832. Min Act: -0.0001

Data Index: 1235590 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.5465. Min Act: -0.0001

Data Index: 1161481 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.3947. Min Act: -0.0001

Data Index: 522078 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.3502. Min Act: -0.0001

Data Index: 1140329 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 5.2756. Min Range: -5.2756

Max Act: 3.3717. Min Act: -0.0001

Data Index: 509833 (C4 (Web Text))

Max Activating Token Index: 853