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

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

Neuron 1958 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: 2.5729. Min Range: -2.5729

Max Act: 2.4963. Min Act: -0.0000

Data Index: 1377880 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.4355. Min Act: -0.0000

Data Index: 1013768 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.2865. Min Act: -0.0000

Data Index: 1568375 (Python Code)

Max Activating Token Index: 976

Text #3

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.2472. Min Act: -0.0000

Data Index: 935101 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.3825. Min Act: -0.0000

Data Index: 102165 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.2555. Min Act: -0.0000

Data Index: 335381 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.3805. Min Act: -0.0000

Data Index: 1555153 (Python Code)

Max Activating Token Index: 785

Text #7

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.3497. Min Act: -0.0000

Data Index: 1430332 (Python Code)

Max Activating Token Index: 946

Text #8

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.4182. Min Act: -0.0000

Data Index: 728181 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.1952. Min Act: -0.0000

Data Index: 1534728 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.5729. Min Act: -0.0000

Data Index: 1282354 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.2022. Min Act: -0.0000

Data Index: 37817 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.4371. Min Act: -0.0000

Data Index: 1548226 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.3845. Min Act: -0.0000

Data Index: 1299102 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.2990. Min Act: -0.0000

Data Index: 92257 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.1804. Min Act: -0.0000

Data Index: 406432 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.2789. Min Act: -0.0000

Data Index: 1468924 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.1592. Min Act: -0.0000

Data Index: 1339473 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.2539. Min Act: -0.0000

Data Index: 1510315 (Python Code)

Max Activating Token Index: 684

Text #19

Max Range: 2.5729. Min Range: -2.5729

Max Act: 2.1511. Min Act: -0.0000

Data Index: 1547363 (Python Code)

Max Activating Token Index: 701