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

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

Neuron 1287 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: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1553233 (Python Code)

Max Activating Token Index: 776

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1395293 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1478978 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1401767 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1622562 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1452799 (Python Code)

Max Activating Token Index: 838

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1631378 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1641659 (Python Code)

Max Activating Token Index: 621

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1400102 (Python Code)

Max Activating Token Index: 693

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1530526 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1429586 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1635153 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1557840 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1594040 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0801. Min Act: -0.0002

Data Index: 598257 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1382636 (Python Code)

Max Activating Token Index: 513

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1474903 (Python Code)

Max Activating Token Index: 503

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1580818 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1480461 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1640878 (Python Code)

Max Activating Token Index: 899