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

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

Neuron 5520 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0887. Min Range: -1.0887

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1639638 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1451342 (Python Code)

Max Activating Token Index: 374

Text #2

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1506954 (Python Code)

Max Activating Token Index: 675

Text #3

Max Range: 1.0887. Min Range: -1.0887

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1425553 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1501850 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8945. Min Act: -0.0000

Data Index: 587103 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1460767 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1449176 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1457578 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1373093 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1361948 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1414770 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1550986 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1361426 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1528468 (Python Code)

Max Activating Token Index: 929

Text #15

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1632387 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1365634 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1405169 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1568179 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1432969 (Python Code)

Max Activating Token Index: 191