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

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

Neuron 226 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.5146. Min Act: -0.0001

Data Index: 603203 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.5425. Min Act: -0.0000

Data Index: 623827 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.2893. Min Act: -0.0000

Data Index: 528277 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.2721. Min Act: -0.0001

Data Index: 604141 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.2080. Min Act: -0.0000

Data Index: 529072 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.2016. Min Act: -0.0000

Data Index: 889096 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.0511. Min Act: -0.0001

Data Index: 1185056 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.1256. Min Act: -0.0000

Data Index: 1108796 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.1011. Min Act: -0.0001

Data Index: 1096396 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.1755. Min Act: -0.0000

Data Index: 490025 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.8840. Min Act: -0.0000

Data Index: 1103230 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.9752. Min Act: -0.0000

Data Index: 143446 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.9566. Min Act: -0.0000

Data Index: 868591 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.9429. Min Act: -0.0000

Data Index: 407982 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.9233. Min Act: -0.0000

Data Index: 605985 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 2.5425. Min Range: -2.5425

Max Act: 2.0223. Min Act: -0.0000

Data Index: 776981 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.8967. Min Act: -0.0001

Data Index: 964455 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.5443. Min Act: -0.0000

Data Index: 672833 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.8971. Min Act: -0.0000

Data Index: 367729 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 2.5425. Min Range: -2.5425

Max Act: 1.9931. Min Act: -0.0000

Data Index: 1060544 (C4 (Web Text))

Max Activating Token Index: 805