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

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

Neuron 1254 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1326. Min Range: -3.1326

Max Act: 3.1326. Min Act: -0.0000

Data Index: 1618704 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.6243. Min Act: -0.0000

Data Index: 1623600 (Python Code)

Max Activating Token Index: 291

Text #2

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.7503. Min Act: -0.0000

Data Index: 1515207 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.7303. Min Act: -0.0000

Data Index: 1440630 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.5619. Min Act: -0.0000

Data Index: 1648387 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.8481. Min Act: -0.0000

Data Index: 1488626 (Python Code)

Max Activating Token Index: 830

Text #6

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.6472. Min Act: -0.0000

Data Index: 1509881 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.4989. Min Act: -0.0000

Data Index: 1590614 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.6027. Min Act: -0.0000

Data Index: 1590555 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.6022. Min Act: -0.0000

Data Index: 1560030 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.5832. Min Act: -0.0000

Data Index: 1533903 (Python Code)

Max Activating Token Index: 276

Text #11

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.7081. Min Act: -0.0000

Data Index: 1436469 (Python Code)

Max Activating Token Index: 270

Text #12

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.4332. Min Act: -0.0000

Data Index: 1618943 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.3930. Min Act: -0.0000

Data Index: 1395797 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.5330. Min Act: -0.0000

Data Index: 1538832 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.3942. Min Act: -0.0000

Data Index: 1362971 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.6527. Min Act: -0.0000

Data Index: 1439242 (Python Code)

Max Activating Token Index: 878

Text #17

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.4815. Min Act: -0.0000

Data Index: 1460145 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.4611. Min Act: -0.0000

Data Index: 1605342 (Python Code)

Max Activating Token Index: 326

Text #19

Max Range: 3.1326. Min Range: -3.1326

Max Act: 2.5645. Min Act: -0.0000

Data Index: 1484255 (Python Code)

Max Activating Token Index: 421