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

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

Neuron 4259 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: 2.7085. Min Range: -2.7085

Max Act: 2.7085. Min Act: -0.0000

Data Index: 1453354 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.5929. Min Act: -0.0000

Data Index: 1630785 (Python Code)

Max Activating Token Index: 436

Text #2

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.6491. Min Act: -0.0000

Data Index: 1424405 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.2608. Min Act: -0.0000

Data Index: 1563150 (Python Code)

Max Activating Token Index: 937

Text #4

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1539215 (Python Code)

Max Activating Token Index: 462

Text #5

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.6684. Min Act: -0.0000

Data Index: 1388363 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.8365. Min Act: -0.0000

Data Index: 1364414 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.7866. Min Act: -0.0000

Data Index: 1389905 (Python Code)

Max Activating Token Index: 653

Text #8

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.7530. Min Act: -0.0000

Data Index: 1645213 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.7248. Min Act: -0.0000

Data Index: 1419471 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.6282. Min Act: -0.0000

Data Index: 1429602 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.1641. Min Act: -0.0000

Data Index: 1469524 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1539952 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.6037. Min Act: -0.0000

Data Index: 1649241 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1514724 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1602071 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.8025. Min Act: -0.0000

Data Index: 1617745 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.6248. Min Act: -0.0000

Data Index: 1465076 (Python Code)

Max Activating Token Index: 942

Text #18

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1590700 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1610916 (Python Code)

Max Activating Token Index: 991