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

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

Neuron 189 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: 0.6604. Min Range: -0.6604

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1384923 (Python Code)

Max Activating Token Index: 869

Text #1

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1420031 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1653299 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1575556 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1578153 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1526743 (Python Code)

Max Activating Token Index: 342

Text #6

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1581380 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1385296 (Python Code)

Max Activating Token Index: 582

Text #8

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1464870 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1454592 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1493198 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1643298 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1385878 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1451919 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1380865 (Python Code)

Max Activating Token Index: 850

Text #15

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1620190 (Python Code)

Max Activating Token Index: 284

Text #16

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1574216 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1578270 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4556. Min Act: -0.0000

Data Index: 602749 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.6604. Min Range: -0.6604

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1178878 (C4 (Web Text))

Max Activating Token Index: 813