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

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

Neuron 6000 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: 2.4305. Min Range: -2.4305

Max Act: 2.4305. Min Act: -0.0001

Data Index: 129380 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.9316. Min Act: -0.0000

Data Index: 991163 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.8554. Min Act: -0.0000

Data Index: 47813 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1080621 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.6894. Min Act: -0.0001

Data Index: 46559 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.7028. Min Act: -0.0000

Data Index: 453928 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.5956. Min Act: -0.0000

Data Index: 456695 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.3865. Min Act: -0.0001

Data Index: 936722 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1189369 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.2920. Min Act: -0.0001

Data Index: 1086048 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1164893 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.0745. Min Act: -0.0001

Data Index: 150736 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.1536. Min Act: -0.0001

Data Index: 1065329 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.1728. Min Act: -0.0000

Data Index: 227708 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 2.4305. Min Range: -2.4305

Max Act: 0.9332. Min Act: -0.0001

Data Index: 1202481 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.1810. Min Act: -0.0001

Data Index: 189028 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 2.4305. Min Range: -2.4305

Max Act: 0.8047. Min Act: -0.0000

Data Index: 489339 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 2.4305. Min Range: -2.4305

Max Act: 0.9336. Min Act: -0.0001

Data Index: 173394 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 2.4305. Min Range: -2.4305

Max Act: 0.9857. Min Act: -0.0000

Data Index: 773344 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.4305. Min Range: -2.4305

Max Act: 1.0054. Min Act: -0.0001

Data Index: 931346 (C4 (Web Text))

Max Activating Token Index: 191