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

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

Neuron 46 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: 0.2773. Min Range: -0.2773

Max Act: 0.2753. Min Act: -0.0001

Data Index: 87648 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2643. Min Act: -0.0001

Data Index: 287664 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2576. Min Act: -0.0001

Data Index: 840011 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2722. Min Act: -0.0001

Data Index: 458639 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2700. Min Act: -0.0001

Data Index: 720086 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2437. Min Act: -0.0001

Data Index: 878408 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2690. Min Act: -0.0001

Data Index: 132035 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2714. Min Act: -0.0001

Data Index: 841062 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2577. Min Act: -0.0001

Data Index: 727300 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1085741 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2386. Min Act: -0.0001

Data Index: 153637 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2288. Min Act: -0.0001

Data Index: 651818 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1147998 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2329. Min Act: -0.0001

Data Index: 921852 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2227. Min Act: -0.0001

Data Index: 446867 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2413. Min Act: -0.0001

Data Index: 946953 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2337. Min Act: -0.0001

Data Index: 274838 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2471. Min Act: -0.0001

Data Index: 248761 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2251. Min Act: -0.0001

Data Index: 1284022 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2096. Min Act: -0.0001

Data Index: 74751 (C4 (Web Text))

Max Activating Token Index: 517