Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 850 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.5234. Min Act: -0.0001

Data Index: 1373730 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1453967 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4265. Min Act: -0.0001

Data Index: 1482606 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4765. Min Act: -0.0001

Data Index: 1461078 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4363. Min Act: -0.0001

Data Index: 1653299 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4395. Min Act: -0.0001

Data Index: 1465005 (Python Code)

Max Activating Token Index: 738

Text #6

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1636210 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4376. Min Act: -0.0001

Data Index: 1637772 (Python Code)

Max Activating Token Index: 59

Text #8

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3876. Min Act: -0.0001

Data Index: 1393365 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4073. Min Act: -0.0001

Data Index: 1496484 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1363948 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3658. Min Act: -0.0001

Data Index: 1628462 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1618344 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4143. Min Act: -0.0001

Data Index: 1579233 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4243. Min Act: -0.0001

Data Index: 1597060 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4077. Min Act: -0.0001

Data Index: 1507444 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4464. Min Act: -0.0001

Data Index: 1428339 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1537566 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1547655 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4155. Min Act: -0.0001

Data Index: 1528329 (Python Code)

Max Activating Token Index: 731