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

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

Neuron 4925 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1603213 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1459801 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1481689 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1391111 (Python Code)

Max Activating Token Index: 882

Text #4

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1386363 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2461. Min Act: 0.0000

Data Index: 1417100 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1408051 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1456633 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1476317 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1464488 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1587349 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1385992 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1612234 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1523701 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1589078 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1391996 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1636002 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1545373 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1521966 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 0.2930. Min Range: -0.2930

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1438990 (Python Code)

Max Activating Token Index: 708