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

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

Neuron 4704 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.3599. Min Act: -0.0000

Data Index: 68894 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1356624 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.2917. Min Act: -0.0000

Data Index: 252300 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.0801. Min Act: -0.0000

Data Index: 358363 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1262102 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.1696. Min Act: -0.0000

Data Index: 510660 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.0191. Min Act: -0.0000

Data Index: 729150 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.0969. Min Act: -0.0000

Data Index: 966321 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.0210. Min Act: -0.0000

Data Index: 306847 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.0063. Min Act: -0.0000

Data Index: 247017 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1310301 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1197729 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.0150. Min Act: -0.0000

Data Index: 358994 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9739. Min Act: -0.0000

Data Index: 698996 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9536. Min Act: -0.0000

Data Index: 852686 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1248782 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1049244 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.0272. Min Act: -0.0001

Data Index: 1298829 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9737. Min Act: -0.0000

Data Index: 259212 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1194739 (C4 (Web Text))

Max Activating Token Index: 359