Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 421 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.5940. Min Act: -0.0002

Data Index: 920662 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.4766. Min Act: -0.0001

Data Index: 499138 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.4127. Min Act: -0.0002

Data Index: 1329636 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.3695. Min Act: -0.0002

Data Index: 1215502 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.1237. Min Act: -0.0001

Data Index: 1263771 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.1454. Min Act: -0.0002

Data Index: 806042 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.1094. Min Act: -0.0002

Data Index: 1325366 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0616. Min Act: -0.0002

Data Index: 1019142 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.1420. Min Act: -0.0002

Data Index: 1097129 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0499. Min Act: -0.0002

Data Index: 260860 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0976. Min Act: -0.0001

Data Index: 720957 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0717. Min Act: -0.0001

Data Index: 746788 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.1024. Min Act: -0.0002

Data Index: 1108131 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0654. Min Act: -0.0002

Data Index: 738259 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0818. Min Act: -0.0002

Data Index: 1350820 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0807. Min Act: -0.0001

Data Index: 238799 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0508. Min Act: -0.0001

Data Index: 58873 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0307. Min Act: -0.0001

Data Index: 258787 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0060. Min Act: -0.0002

Data Index: 801915 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.5940. Min Range: -1.5940

Max Act: 1.0345. Min Act: -0.0002

Data Index: 105916 (C4 (Web Text))

Max Activating Token Index: 165