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

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

Neuron 1189 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2760. Min Act: -0.0000

Data Index: 964081 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1045570 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1114945 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2022. Min Act: -0.0000

Data Index: 676360 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1279894 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2168. Min Act: -0.0000

Data Index: 660960 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2195. Min Act: -0.0000

Data Index: 917284 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1000568 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1061343 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2102. Min Act: -0.0000

Data Index: 445859 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2085. Min Act: -0.0000

Data Index: 557353 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.1986. Min Act: -0.0000

Data Index: 302603 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2014. Min Act: -0.0000

Data Index: 236434 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2005. Min Act: -0.0000

Data Index: 971003 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2029. Min Act: -0.0000

Data Index: 988435 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2020. Min Act: -0.0000

Data Index: 819468 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.1894. Min Act: -0.0000

Data Index: 397247 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.1993. Min Act: -0.0000

Data Index: 485316 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.1910. Min Act: -0.0000

Data Index: 668581 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.1873. Min Act: -0.0000

Data Index: 469058 (C4 (Web Text))

Max Activating Token Index: 470