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

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

Neuron 3745 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1234. Min Range: -1.1234

Max Act: 1.1234. Min Act: -0.0002

Data Index: 1411671 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.9977. Min Act: -0.0002

Data Index: 1647446 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.9854. Min Act: -0.0002

Data Index: 1567604 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8884. Min Act: -0.0002

Data Index: 1565532 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8929. Min Act: -0.0002

Data Index: 1538156 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8851. Min Act: -0.0002

Data Index: 1540582 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.9000. Min Act: -0.0002

Data Index: 1512969 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8651. Min Act: -0.0002

Data Index: 1650492 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8768. Min Act: -0.0002

Data Index: 1491960 (Python Code)

Max Activating Token Index: 520

Text #9

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8502. Min Act: -0.0002

Data Index: 1377386 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8591. Min Act: -0.0002

Data Index: 1360985 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8685. Min Act: -0.0002

Data Index: 1450281 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8267. Min Act: -0.0002

Data Index: 1416541 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8202. Min Act: -0.0002

Data Index: 1367886 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8040. Min Act: -0.0002

Data Index: 1370368 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8128. Min Act: -0.0002

Data Index: 1593492 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8159. Min Act: -0.0002

Data Index: 1481657 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8157. Min Act: -0.0002

Data Index: 1361608 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7891. Min Act: -0.0002

Data Index: 1419022 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7923. Min Act: -0.0002

Data Index: 1371201 (Python Code)

Max Activating Token Index: 662