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

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

Neuron 2827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1073933 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.8148. Min Act: -0.0000

Data Index: 274846 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7502. Min Act: -0.0000

Data Index: 317912 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6830. Min Act: -0.0000

Data Index: 783172 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5969. Min Act: -0.0000

Data Index: 907777 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1274409 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1351259 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6443. Min Act: -0.0000

Data Index: 987618 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5533. Min Act: -0.0000

Data Index: 756161 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6908. Min Act: -0.0000

Data Index: 110713 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6329. Min Act: -0.0000

Data Index: 388784 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1172898 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1588575 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6042. Min Act: -0.0000

Data Index: 435402 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1192949 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1124772 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5386. Min Act: -0.0000

Data Index: 323579 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5995. Min Act: -0.0000

Data Index: 416503 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5853. Min Act: -0.0000

Data Index: 820517 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6137. Min Act: -0.0000

Data Index: 334653 (C4 (Web Text))

Max Activating Token Index: 260