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

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

Neuron 1581 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.8399. Min Act: -0.0000

Data Index: 1523798 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1379578 (Python Code)

Max Activating Token Index: 907

Text #2

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1650794 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1378304 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.6834. Min Act: -0.0000

Data Index: 1360479 (Python Code)

Max Activating Token Index: 1007

Text #5

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.5892. Min Act: -0.0000

Data Index: 1586365 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1641098 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1606663 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1554116 (Python Code)

Max Activating Token Index: 256

Text #9

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.5548. Min Act: -0.0000

Data Index: 1579814 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1516662 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1410146 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.3872. Min Act: -0.0000

Data Index: 1378527 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1616554 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4661. Min Act: -0.0000

Data Index: 1614370 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1613769 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1422744 (Python Code)

Max Activating Token Index: 785

Text #17

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.5221. Min Act: -0.0000

Data Index: 1400999 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4296. Min Act: -0.0000

Data Index: 1569972 (Python Code)

Max Activating Token Index: 50

Text #19

Max Range: 1.8399. Min Range: -1.8399

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1580825 (Python Code)

Max Activating Token Index: 281