Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5003 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0768. Min Range: -4.0768

Max Act: 4.0355. Min Act: -0.0000

Data Index: 831343 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 4.0768. Min Range: -4.0768

Max Act: 4.0237. Min Act: -0.0000

Data Index: 990766 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 4.0768. Min Range: -4.0768

Max Act: 4.0768. Min Act: -0.0000

Data Index: 1202117 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.7265. Min Act: -0.0000

Data Index: 840505 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.7555. Min Act: -0.0000

Data Index: 651712 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.7153. Min Act: -0.0000

Data Index: 154720 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.5695. Min Act: -0.0000

Data Index: 1223494 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.6994. Min Act: -0.0000

Data Index: 678222 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.8021. Min Act: -0.0000

Data Index: 842037 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.5213. Min Act: -0.0000

Data Index: 38640 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.5735. Min Act: -0.0000

Data Index: 939009 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.2921. Min Act: -0.0000

Data Index: 129577 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.5715. Min Act: -0.0000

Data Index: 1124407 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.1923. Min Act: -0.0000

Data Index: 752652 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.2474. Min Act: -0.0000

Data Index: 536871 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.2370. Min Act: -0.0000

Data Index: 1212770 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.2475. Min Act: -0.0000

Data Index: 282681 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.2013. Min Act: -0.0000

Data Index: 474881 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.2300. Min Act: -0.0000

Data Index: 625843 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 4.0768. Min Range: -4.0768

Max Act: 3.0838. Min Act: -0.0000

Data Index: 978239 (C4 (Web Text))

Max Activating Token Index: 894