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

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

Neuron 4021 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: 1.6600. Min Range: -1.6600

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1574285 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1550317 (Python Code)

Max Activating Token Index: 934

Text #2

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1478799 (Python Code)

Max Activating Token Index: 602

Text #3

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.6564. Min Act: -0.0000

Data Index: 1442069 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.5114. Min Act: -0.0000

Data Index: 1506346 (Python Code)

Max Activating Token Index: 366

Text #5

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.6443. Min Act: -0.0000

Data Index: 1589997 (Python Code)

Max Activating Token Index: 563

Text #6

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1651358 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.5450. Min Act: -0.0000

Data Index: 1385531 (Python Code)

Max Activating Token Index: 432

Text #8

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1652775 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1380283 (Python Code)

Max Activating Token Index: 138

Text #10

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1645712 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4807. Min Act: -0.0000

Data Index: 1387206 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4320. Min Act: -0.0000

Data Index: 1573962 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1582616 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3922. Min Act: -0.0000

Data Index: 1474545 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1364725 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3694. Min Act: -0.0000

Data Index: 1446308 (Python Code)

Max Activating Token Index: 779

Text #17

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1561136 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4372. Min Act: -0.0000

Data Index: 1604178 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1565040 (Python Code)

Max Activating Token Index: 18