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

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

Neuron 4299 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.4444. Min Act: -0.0000

Data Index: 329213 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2448. Min Act: -0.0000

Data Index: 698897 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2295. Min Act: -0.0000

Data Index: 916721 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1931. Min Act: 0.0003

Data Index: 120643 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2884. Min Act: 0.0000

Data Index: 994316 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1855. Min Act: -0.0000

Data Index: 211507 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1325. Min Act: -0.0000

Data Index: 707093 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1342808 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1160. Min Act: -0.0000

Data Index: 824421 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0786. Min Act: -0.0000

Data Index: 369346 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1204393 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0209. Min Act: -0.0000

Data Index: 69387 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0764. Min Act: -0.0000

Data Index: 920912 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1285887 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0346. Min Act: -0.0000

Data Index: 523583 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9963. Min Act: -0.0000

Data Index: 203608 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0226. Min Act: -0.0000

Data Index: 870061 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1026188 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9970. Min Act: 0.0001

Data Index: 1273382 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1299. Min Act: -0.0000

Data Index: 129156 (C4 (Web Text))

Max Activating Token Index: 638