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

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

Neuron 2920 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.3068. Min Act: -0.0000

Data Index: 1594995 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1551655 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.0806. Min Act: -0.0000

Data Index: 1448053 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.9727. Min Act: -0.0000

Data Index: 1413613 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.0489. Min Act: -0.0000

Data Index: 1541406 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.9229. Min Act: -0.0000

Data Index: 1609708 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.9215. Min Act: -0.0000

Data Index: 1495086 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.8967. Min Act: -0.0000

Data Index: 1508833 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.8934. Min Act: -0.0000

Data Index: 1620820 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.8444. Min Act: -0.0000

Data Index: 1643639 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.6876. Min Act: -0.0000

Data Index: 1501597 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.7630. Min Act: -0.0000

Data Index: 1389973 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.7275. Min Act: -0.0000

Data Index: 1623473 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.8212. Min Act: -0.0000

Data Index: 1637646 (Python Code)

Max Activating Token Index: 34

Text #14

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.6934. Min Act: -0.0000

Data Index: 1468349 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1522152 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.5309. Min Act: -0.0000

Data Index: 1590796 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.6164. Min Act: -0.0000

Data Index: 1620851 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1548199 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.3068. Min Range: -2.3068

Max Act: 1.6059. Min Act: -0.0000

Data Index: 1592036 (Python Code)

Max Activating Token Index: 25