Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.3583. Min Range: -2.3583

Max Act: 2.3583. Min Act: -0.0001

Data Index: 1631563 (Python Code)

Max Activating Token Index: 283

Text #1

Max Range: 2.3583. Min Range: -2.3583

Max Act: 2.2835. Min Act: -0.0000

Data Index: 1593256 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 2.3583. Min Range: -2.3583

Max Act: 2.2254. Min Act: -0.0001

Data Index: 1616520 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 2.3583. Min Range: -2.3583

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1454356 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 2.3583. Min Range: -2.3583

Max Act: 2.1635. Min Act: -0.0000

Data Index: 1557524 (Python Code)

Max Activating Token Index: 403

Text #5

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.9205. Min Act: -0.0000

Data Index: 1401371 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 2.3583. Min Range: -2.3583

Max Act: 2.0073. Min Act: -0.0000

Data Index: 1360140 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 2.3583. Min Range: -2.3583

Max Act: 2.0185. Min Act: -0.0001

Data Index: 1372980 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.8976. Min Act: -0.0000

Data Index: 1424011 (Python Code)

Max Activating Token Index: 910

Text #9

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.9428. Min Act: -0.0000

Data Index: 1456371 (Python Code)

Max Activating Token Index: 922

Text #10

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.9530. Min Act: -0.0000

Data Index: 1465712 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.8256. Min Act: -0.0000

Data Index: 1490216 (Python Code)

Max Activating Token Index: 575

Text #12

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.9610. Min Act: -0.0000

Data Index: 1613662 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.8564. Min Act: -0.0000

Data Index: 1459144 (Python Code)

Max Activating Token Index: 991

Text #14

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.7986. Min Act: -0.0000

Data Index: 1379251 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1387484 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.8142. Min Act: -0.0001

Data Index: 1427352 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.8072. Min Act: -0.0001

Data Index: 1504664 (Python Code)

Max Activating Token Index: 443

Text #18

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.7853. Min Act: -0.0000

Data Index: 1520908 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 2.3583. Min Range: -2.3583

Max Act: 1.7125. Min Act: -0.0000

Data Index: 1552644 (Python Code)

Max Activating Token Index: 279