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

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

Neuron 1815 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8987. Min Act: -0.0000

Data Index: 1417503 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7139. Min Act: -0.0000

Data Index: 1362458 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8359. Min Act: -0.0000

Data Index: 1468683 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1595991 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7081. Min Act: -0.0000

Data Index: 1366718 (Python Code)

Max Activating Token Index: 88

Text #5

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1498876 (Python Code)

Max Activating Token Index: 834

Text #6

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7178. Min Act: -0.0000

Data Index: 1400623 (Python Code)

Max Activating Token Index: 837

Text #7

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1526689 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1478335 (Python Code)

Max Activating Token Index: 890

Text #9

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1510844 (Python Code)

Max Activating Token Index: 536

Text #10

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1390286 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1591113 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1410786 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1467672 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1501998 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1412873 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.5088. Min Act: -0.0000

Data Index: 1459514 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1417100 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.4926. Min Act: -0.0000

Data Index: 1608233 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1605205 (Python Code)

Max Activating Token Index: 366