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

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

Neuron 2747 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1463378 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0997. Min Act: -0.0000

Data Index: 835343 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1518033 (Python Code)

Max Activating Token Index: 426

Text #3

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1596121 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1227695 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1447644 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1489615 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1591862 (Python Code)

Max Activating Token Index: 148

Text #8

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0791. Min Act: -0.0000

Data Index: 479824 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1102506 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1192188 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0738. Min Act: -0.0000

Data Index: 593823 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1444915 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1516940 (Python Code)

Max Activating Token Index: 820

Text #14

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0704. Min Act: -0.0001

Data Index: 471485 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1186948 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1577147 (Python Code)

Max Activating Token Index: 765

Text #17

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1404243 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0647. Min Act: -0.0001

Data Index: 36554 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1576333 (Python Code)

Max Activating Token Index: 562