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

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

Neuron 5279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1449472 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1383694 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1519754 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1436307 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1509257 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1519660 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1447654 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1518381 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1622751 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1419453 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1529774 (Python Code)

Max Activating Token Index: 825

Text #11

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1396229 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1643680 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1653711 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1529635 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1413574 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1577471 (Python Code)

Max Activating Token Index: 994

Text #17

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6706. Min Act: -0.0000

Data Index: 642191 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1414926 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1433003 (Python Code)

Max Activating Token Index: 430