Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.7948. Min Act: -0.0000

Data Index: 1448770 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.6342. Min Act: -0.0000

Data Index: 1586853 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.4898. Min Act: -0.0000

Data Index: 1639806 (Python Code)

Max Activating Token Index: 787

Text #3

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.5368. Min Act: -0.0000

Data Index: 1550472 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.2918. Min Act: -0.0000

Data Index: 1553323 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.5145. Min Act: -0.0000

Data Index: 1426641 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.6385. Min Act: -0.0000

Data Index: 1506729 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.6258. Min Act: -0.0000

Data Index: 1402301 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.6350. Min Act: -0.0000

Data Index: 1491228 (Python Code)

Max Activating Token Index: 336

Text #9

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.6446. Min Act: -0.0000

Data Index: 1489851 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.7596. Min Act: -0.0000

Data Index: 1499716 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.5833. Min Act: -0.0000

Data Index: 1623495 (Python Code)

Max Activating Token Index: 159

Text #12

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.5286. Min Act: -0.0000

Data Index: 1645929 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.6370. Min Act: -0.0000

Data Index: 1506557 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.3860. Min Act: -0.0000

Data Index: 1546967 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.3952. Min Act: -0.0000

Data Index: 1602358 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.5086. Min Act: -0.0000

Data Index: 1570841 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.5157. Min Act: -0.0000

Data Index: 1596735 (Python Code)

Max Activating Token Index: 395

Text #18

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.3638. Min Act: -0.0000

Data Index: 1539270 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 2.7948. Min Range: -2.7948

Max Act: 2.3863. Min Act: -0.0000

Data Index: 1619671 (Python Code)

Max Activating Token Index: 505