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

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

Neuron 1946 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: 5.7064. Min Range: -5.7064

Max Act: 5.4233. Min Act: -0.0000

Data Index: 1342888 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 5.7064. Min Range: -5.7064

Max Act: 5.5157. Min Act: -0.0000

Data Index: 628462 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 5.7064. Min Range: -5.7064

Max Act: 5.7064. Min Act: -0.0000

Data Index: 762469 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 5.7064. Min Range: -5.7064

Max Act: 5.4879. Min Act: -0.0000

Data Index: 288533 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 5.7064. Min Range: -5.7064

Max Act: 5.3729. Min Act: -0.0000

Data Index: 805977 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 5.7064. Min Range: -5.7064

Max Act: 5.0586. Min Act: -0.0000

Data Index: 938427 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 5.7064. Min Range: -5.7064

Max Act: 5.0498. Min Act: -0.0000

Data Index: 1310031 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.9455. Min Act: -0.0000

Data Index: 1134840 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.9474. Min Act: -0.0000

Data Index: 489749 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.9495. Min Act: -0.0000

Data Index: 312291 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.9228. Min Act: -0.0000

Data Index: 431372 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.9180. Min Act: -0.0000

Data Index: 53038 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.9248. Min Act: -0.0000

Data Index: 873536 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.9102. Min Act: -0.0000

Data Index: 4439 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.8678. Min Act: -0.0000

Data Index: 567311 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.6269. Min Act: -0.0000

Data Index: 190698 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.7916. Min Act: -0.0000

Data Index: 944748 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.5948. Min Act: -0.0000

Data Index: 461049 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.7648. Min Act: -0.0000

Data Index: 1224876 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 5.7064. Min Range: -5.7064

Max Act: 4.7511. Min Act: -0.0000

Data Index: 224515 (C4 (Web Text))

Max Activating Token Index: 112