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

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

Neuron 253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1871. Min Range: -1.1871

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1387485 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 1.1871. Min Range: -1.1871

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1541281 (Python Code)

Max Activating Token Index: 633

Text #2

Max Range: 1.1871. Min Range: -1.1871

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1636550 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1498495 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1487647 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1525235 (Python Code)

Max Activating Token Index: 926

Text #6

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1391526 (Python Code)

Max Activating Token Index: 610

Text #7

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1552325 (Python Code)

Max Activating Token Index: 1001

Text #8

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1569001 (Python Code)

Max Activating Token Index: 596

Text #9

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1399829 (Python Code)

Max Activating Token Index: 479

Text #10

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1459366 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1649697 (Python Code)

Max Activating Token Index: 209

Text #12

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1377976 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1446847 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1393127 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1469799 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1401519 (Python Code)

Max Activating Token Index: 941

Text #17

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1491988 (Python Code)

Max Activating Token Index: 337

Text #18

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1438711 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1409594 (Python Code)

Max Activating Token Index: 652