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

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

Neuron 4093 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: 4.9385. Min Range: -4.9385

Max Act: 4.9385. Min Act: -0.0000

Data Index: 1637900 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 4.9385. Min Range: -4.9385

Max Act: 3.7422. Min Act: -0.0000

Data Index: 1446712 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 4.9385. Min Range: -4.9385

Max Act: 3.2426. Min Act: -0.0000

Data Index: 1612917 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 4.9385. Min Range: -4.9385

Max Act: 3.2154. Min Act: -0.0000

Data Index: 1546723 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 4.9385. Min Range: -4.9385

Max Act: 3.0888. Min Act: 0.0000

Data Index: 1432675 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 4.9385. Min Range: -4.9385

Max Act: 3.0684. Min Act: -0.0000

Data Index: 1386072 (Python Code)

Max Activating Token Index: 770

Text #6

Max Range: 4.9385. Min Range: -4.9385

Max Act: 3.2259. Min Act: -0.0000

Data Index: 1640480 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.7652. Min Act: -0.0000

Data Index: 1459415 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 4.9385. Min Range: -4.9385

Max Act: 3.0045. Min Act: -0.0000

Data Index: 1640894 (Python Code)

Max Activating Token Index: 296

Text #9

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.9143. Min Act: 0.0000

Data Index: 1539904 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.8412. Min Act: -0.0000

Data Index: 1559103 (Python Code)

Max Activating Token Index: 523

Text #11

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.7876. Min Act: -0.0000

Data Index: 1425518 (Python Code)

Max Activating Token Index: 615

Text #12

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.6665. Min Act: 0.0000

Data Index: 1475155 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.7735. Min Act: 0.0000

Data Index: 1605835 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.8220. Min Act: -0.0000

Data Index: 1626579 (Python Code)

Max Activating Token Index: 609

Text #15

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.6972. Min Act: -0.0000

Data Index: 1475002 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.6398. Min Act: -0.0000

Data Index: 1465024 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.3621. Min Act: -0.0000

Data Index: 1526340 (Python Code)

Max Activating Token Index: 923

Text #18

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.5464. Min Act: -0.0000

Data Index: 1461716 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 4.9385. Min Range: -4.9385

Max Act: 2.6743. Min Act: -0.0000

Data Index: 1494360 (Python Code)

Max Activating Token Index: 218