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

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

Neuron 5353 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1148. Min Range: -1.1148

Max Act: 1.1067. Min Act: -0.0001

Data Index: 1482122 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 1.1148. Min Range: -1.1148

Max Act: 1.0578. Min Act: -0.0001

Data Index: 385849 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.1148. Min Range: -1.1148

Max Act: 1.0540. Min Act: -0.0001

Data Index: 1551751 (Python Code)

Max Activating Token Index: 287

Text #3

Max Range: 1.1148. Min Range: -1.1148

Max Act: 1.1148. Min Act: -0.0001

Data Index: 1655194 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9577. Min Act: -0.0002

Data Index: 45467 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.1148. Min Range: -1.1148

Max Act: 1.0132. Min Act: -0.0001

Data Index: 1200767 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.1148. Min Range: -1.1148

Max Act: 1.0528. Min Act: -0.0002

Data Index: 355654 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 1.1148. Min Range: -1.1148

Max Act: 1.0475. Min Act: -0.0001

Data Index: 53607 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9296. Min Act: -0.0001

Data Index: 626175 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9698. Min Act: -0.0001

Data Index: 1416404 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8473. Min Act: -0.0001

Data Index: 1508221 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9162. Min Act: -0.0001

Data Index: 1637997 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9391. Min Act: -0.0001

Data Index: 1419160 (Python Code)

Max Activating Token Index: 256

Text #13

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1416440 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8502. Min Act: -0.0001

Data Index: 1444049 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.7861. Min Act: -0.0001

Data Index: 1544688 (Python Code)

Max Activating Token Index: 776

Text #16

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8734. Min Act: -0.0001

Data Index: 1438696 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.6949. Min Act: -0.0001

Data Index: 1522773 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8871. Min Act: -0.0001

Data Index: 741874 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8618. Min Act: -0.0001

Data Index: 1443725 (Python Code)

Max Activating Token Index: 508