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

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

Neuron 2902 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0557. Min Range: -2.0557

Max Act: 2.0557. Min Act: -0.0000

Data Index: 1078867 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1038934 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.4759. Min Act: -0.0000

Data Index: 238809 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.4760. Min Act: -0.0000

Data Index: 757888 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.3415. Min Act: -0.0000

Data Index: 203094 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1173268 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1117541 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.2125. Min Act: -0.0000

Data Index: 982709 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1021891 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.1768. Min Act: -0.0000

Data Index: 695599 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.1582. Min Act: -0.0000

Data Index: 694216 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.1584. Min Act: 0.0000

Data Index: 413051 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.1395. Min Act: -0.0000

Data Index: 804041 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.1300. Min Act: -0.0000

Data Index: 474949 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1196432 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.1350. Min Act: -0.0000

Data Index: 401337 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.1049. Min Act: -0.0000

Data Index: 692736 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.0043. Min Act: -0.0000

Data Index: 477099 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.0257. Min Act: -0.0000

Data Index: 62779 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 2.0557. Min Range: -2.0557

Max Act: 1.0861. Min Act: -0.0000

Data Index: 79645 (C4 (Web Text))

Max Activating Token Index: 64