Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 852 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.8305. Min Act: -0.0001

Data Index: 1464948 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.7464. Min Act: -0.0001

Data Index: 1625667 (Python Code)

Max Activating Token Index: 657

Text #2

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.7746. Min Act: -0.0001

Data Index: 1632363 (Python Code)

Max Activating Token Index: 799

Text #3

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1608141 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6984. Min Act: -0.0001

Data Index: 1511225 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1430853 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6680. Min Act: -0.0001

Data Index: 1436007 (Python Code)

Max Activating Token Index: 212

Text #7

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1437725 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1555478 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6510. Min Act: -0.0001

Data Index: 1424047 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6347. Min Act: -0.0001

Data Index: 1570271 (Python Code)

Max Activating Token Index: 838

Text #11

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6169. Min Act: -0.0001

Data Index: 1484824 (Python Code)

Max Activating Token Index: 886

Text #12

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1438222 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6305. Min Act: -0.0001

Data Index: 1613808 (Python Code)

Max Activating Token Index: 455

Text #14

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6315. Min Act: -0.0001

Data Index: 1385012 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6038. Min Act: -0.0001

Data Index: 1637848 (Python Code)

Max Activating Token Index: 278

Text #16

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1472356 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5963. Min Act: -0.0001

Data Index: 1447986 (Python Code)

Max Activating Token Index: 743

Text #18

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1393858 (Python Code)

Max Activating Token Index: 602

Text #19

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5756. Min Act: -0.0001

Data Index: 1476881 (Python Code)

Max Activating Token Index: 970