Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2629 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.9074. Min Act: -0.0001

Data Index: 1365519 (Python Code)

Max Activating Token Index: 870

Text #1

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.5804. Min Act: -0.0001

Data Index: 1535871 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.6152. Min Act: -0.0001

Data Index: 1637177 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.6615. Min Act: -0.0001

Data Index: 1563966 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.7434. Min Act: -0.0001

Data Index: 1503386 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.7811. Min Act: -0.0001

Data Index: 1604272 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.8250. Min Act: -0.0001

Data Index: 1442920 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.5776. Min Act: -0.0001

Data Index: 1656399 (Python Code)

Max Activating Token Index: 541

Text #8

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.7036. Min Act: -0.0001

Data Index: 1613937 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.6964. Min Act: -0.0001

Data Index: 1646481 (Python Code)

Max Activating Token Index: 573

Text #10

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.6146. Min Act: -0.0001

Data Index: 1467744 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.6094. Min Act: -0.0001

Data Index: 1475329 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.4760. Min Act: -0.0001

Data Index: 1581347 (Python Code)

Max Activating Token Index: 623

Text #13

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.6454. Min Act: -0.0001

Data Index: 1596575 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.5683. Min Act: -0.0001

Data Index: 1387031 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.4722. Min Act: -0.0001

Data Index: 1521728 (Python Code)

Max Activating Token Index: 611

Text #16

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.4730. Min Act: -0.0001

Data Index: 1581421 (Python Code)

Max Activating Token Index: 700

Text #17

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.7254. Min Act: -0.0001

Data Index: 1489755 (Python Code)

Max Activating Token Index: 55

Text #18

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.5024. Min Act: -0.0001

Data Index: 1522098 (Python Code)

Max Activating Token Index: 396

Text #19

Max Range: 1.9074. Min Range: -1.9074

Max Act: 1.6689. Min Act: -0.0001

Data Index: 1559357 (Python Code)

Max Activating Token Index: 919