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

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

Neuron 1803 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.2282. Min Act: -0.0000

Data Index: 284666 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1118426 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1169903 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.2476. Min Act: -0.0000

Data Index: 783187 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1076891 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.0250. Min Act: -0.0000

Data Index: 913382 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1411211 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1246920 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.0028. Min Act: -0.0000

Data Index: 125329 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1571156 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1439845 (Python Code)

Max Activating Token Index: 860

Text #11

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1451029 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9326. Min Act: -0.0000

Data Index: 182413 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1491120 (Python Code)

Max Activating Token Index: 1021

Text #14

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1517148 (Python Code)

Max Activating Token Index: 192

Text #15

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1175994 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9161. Min Act: -0.0000

Data Index: 536841 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1205999 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1284443 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1242846 (C4 (Web Text))

Max Activating Token Index: 103