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

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

Neuron 1288 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.6543. Min Act: -0.0001

Data Index: 1610531 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.5028. Min Act: -0.0001

Data Index: 1166207 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.4949. Min Act: -0.0001

Data Index: 504857 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.3233. Min Act: -0.0001

Data Index: 692215 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.4386. Min Act: -0.0001

Data Index: 970152 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.3295. Min Act: -0.0001

Data Index: 226903 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.3329. Min Act: -0.0001

Data Index: 1532556 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.2844. Min Act: -0.0001

Data Index: 1471573 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.2098. Min Act: -0.0001

Data Index: 1489039 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.2220. Min Act: -0.0001

Data Index: 1524432 (Python Code)

Max Activating Token Index: 502

Text #10

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.1024. Min Act: -0.0001

Data Index: 20323 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1395671 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.1926. Min Act: -0.0001

Data Index: 1576722 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.1836. Min Act: -0.0001

Data Index: 1478298 (Python Code)

Max Activating Token Index: 391

Text #14

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.1283. Min Act: -0.0001

Data Index: 1620410 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.0900. Min Act: -0.0001

Data Index: 1291223 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.1119. Min Act: -0.0001

Data Index: 1563674 (Python Code)

Max Activating Token Index: 739

Text #17

Max Range: 1.6543. Min Range: -1.6543

Max Act: 1.2356. Min Act: -0.0001

Data Index: 201656 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.6543. Min Range: -1.6543

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1072660 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.6543. Min Range: -1.6543

Max Act: 0.9318. Min Act: -0.0001

Data Index: 1119355 (C4 (Web Text))

Max Activating Token Index: 736