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

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

Neuron 2065 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: 0.5972. Min Range: -0.5972

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1449045 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5508. Min Act: -0.0000

Data Index: 92293 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5278. Min Act: -0.0000

Data Index: 982715 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5445. Min Act: -0.0000

Data Index: 330672 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1084623 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1212399 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4861. Min Act: -0.0000

Data Index: 784060 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5084. Min Act: -0.0000

Data Index: 768989 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1347147 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1341756 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4865. Min Act: -0.0000

Data Index: 832850 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4268. Min Act: -0.0000

Data Index: 31848 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1100398 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4538. Min Act: -0.0000

Data Index: 532933 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4829. Min Act: -0.0000

Data Index: 871040 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4451. Min Act: -0.0000

Data Index: 557149 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4584. Min Act: -0.0000

Data Index: 613435 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1577999 (Python Code)

Max Activating Token Index: 273

Text #18

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4597. Min Act: -0.0000

Data Index: 395080 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1603511 (Python Code)

Max Activating Token Index: 490