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

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

Neuron 3000 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5941. Min Act: -0.0000

Data Index: 204109 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5748. Min Act: -0.0000

Data Index: 303981 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1207657 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1262220 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5400. Min Act: -0.0000

Data Index: 585675 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5080. Min Act: -0.0000

Data Index: 442327 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5361. Min Act: -0.0000

Data Index: 350939 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1312140 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1020858 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5079. Min Act: -0.0000

Data Index: 627563 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5367. Min Act: -0.0000

Data Index: 417508 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5002. Min Act: -0.0000

Data Index: 35380 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5213. Min Act: -0.0000

Data Index: 884863 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5170. Min Act: -0.0000

Data Index: 848820 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.4454. Min Act: -0.0000

Data Index: 966589 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1206592 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1137561 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.4750. Min Act: -0.0000

Data Index: 335799 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.5060. Min Act: -0.0000

Data Index: 838764 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.5941. Min Range: -0.5941

Max Act: 0.4832. Min Act: -0.0000

Data Index: 754311 (C4 (Web Text))

Max Activating Token Index: 450