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

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

Neuron 5393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1608393 (Python Code)

Max Activating Token Index: 559

Text #1

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1569135 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1447312 (Python Code)

Max Activating Token Index: 533

Text #3

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1528189 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1591111 (Python Code)

Max Activating Token Index: 583

Text #5

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1401148 (Python Code)

Max Activating Token Index: 291

Text #6

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1456840 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6316. Min Act: -0.0000

Data Index: 360430 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1497070 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1418460 (Python Code)

Max Activating Token Index: 705

Text #10

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1508619 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1594018 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1607954 (Python Code)

Max Activating Token Index: 355

Text #13

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1504926 (Python Code)

Max Activating Token Index: 442

Text #14

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1621315 (Python Code)

Max Activating Token Index: 833

Text #15

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1568293 (Python Code)

Max Activating Token Index: 268

Text #16

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1624525 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1420110 (Python Code)

Max Activating Token Index: 747

Text #18

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1536771 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1500191 (Python Code)

Max Activating Token Index: 191