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

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

Neuron 4230 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.3723. Min Act: -0.0000

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1441. Min Act: -0.0000

Data Index: 391415 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 4.3723. Min Range: -4.3723

Max Act: 3.2548. Min Act: -0.0000

Data Index: 129639 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 4.3723. Min Range: -4.3723

Max Act: 3.0400. Min Act: -0.0000

Data Index: 363789 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 4.3723. Min Range: -4.3723

Max Act: 3.0234. Min Act: -0.0000

Data Index: 343844 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 4.3723. Min Range: -4.3723

Max Act: 3.1403. Min Act: -0.0000

Data Index: 578810 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.9213. Min Act: -0.0000

Data Index: 1006805 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1355404 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.7807. Min Act: -0.0000

Data Index: 814017 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.6139. Min Act: -0.0000

Data Index: 307594 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.7267. Min Act: -0.0000

Data Index: 448927 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.7079. Min Act: -0.0000

Data Index: 1247982 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.6806. Min Act: -0.0000

Data Index: 697274 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.6460. Min Act: -0.0000

Data Index: 379755 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.5300. Min Act: -0.0000

Data Index: 1116040 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.6324. Min Act: -0.0000

Data Index: 821166 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.6020. Min Act: -0.0000

Data Index: 78297 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.7188. Min Act: -0.0000

Data Index: 21590 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.4461. Min Act: -0.0000

Data Index: 1271439 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 4.3723. Min Range: -4.3723

Max Act: 2.5436. Min Act: -0.0000

Data Index: 791096 (C4 (Web Text))

Max Activating Token Index: 789