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

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

Neuron 1806 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0519. Min Range: -5.0519

Max Act: 5.0519. Min Act: -0.0000

Data Index: 293065 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8082. Min Act: -0.0000

Data Index: 33219 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.2307. Min Act: -0.0000

Data Index: 1532070 (Python Code)

Max Activating Token Index: 1005

Text #3

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.2022. Min Act: -0.0000

Data Index: 540745 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.1461. Min Act: -0.0000

Data Index: 1444899 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.9744. Min Act: -0.0000

Data Index: 1381085 (Python Code)

Max Activating Token Index: 678

Text #6

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.8112. Min Act: -0.0000

Data Index: 1382533 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.0172. Min Act: -0.0000

Data Index: 1571136 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.6762. Min Act: -0.0000

Data Index: 1644338 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.9467. Min Act: -0.0000

Data Index: 1391561 (Python Code)

Max Activating Token Index: 936

Text #10

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.7948. Min Act: -0.0000

Data Index: 1464192 (Python Code)

Max Activating Token Index: 233

Text #11

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.7622. Min Act: -0.0000

Data Index: 1466106 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.6741. Min Act: -0.0000

Data Index: 1516246 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.8059. Min Act: -0.0000

Data Index: 871046 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.9546. Min Act: -0.0000

Data Index: 293625 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.6049. Min Act: -0.0000

Data Index: 1518985 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.5284. Min Act: -0.0000

Data Index: 1419645 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.4724. Min Act: -0.0000

Data Index: 1644546 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.3622. Min Act: -0.0000

Data Index: 1399269 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 5.0519. Min Range: -5.0519

Max Act: 3.1468. Min Act: -0.0000

Data Index: 1586250 (Python Code)

Max Activating Token Index: 381