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

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

Neuron 3361 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1602509 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1146. Min Act: -0.0001

Data Index: 881539 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1443446 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1644505 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1509263 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1470693 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1542629 (Python Code)

Max Activating Token Index: 403

Text #7

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1403910 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1657030 (Python Code)

Max Activating Token Index: 118

Text #9

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1432920 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1527036 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1450470 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1554476 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1386103 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1587417 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1615034 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1547588 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1571134 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1441610 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1586785 (Python Code)

Max Activating Token Index: 281