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

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

Neuron 4797 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.9787. Min Act: -0.0000

Data Index: 64276 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.7515. Min Act: -0.0000

Data Index: 1315180 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.8444. Min Act: -0.0000

Data Index: 167792 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.7934. Min Act: -0.0000

Data Index: 481405 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4864. Min Act: -0.0000

Data Index: 291303 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.6898. Min Act: -0.0000

Data Index: 844186 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4143. Min Act: -0.0000

Data Index: 376901 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1004004 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.6465. Min Act: -0.0000

Data Index: 398139 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.5057. Min Act: -0.0000

Data Index: 192698 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4651. Min Act: -0.0000

Data Index: 634872 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.5926. Min Act: -0.0000

Data Index: 569537 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4682. Min Act: -0.0000

Data Index: 482464 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4491. Min Act: -0.0000

Data Index: 403688 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4343. Min Act: -0.0000

Data Index: 585832 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.2977. Min Act: -0.0000

Data Index: 61560 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.2879. Min Act: -0.0000

Data Index: 758887 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.2243. Min Act: -0.0000

Data Index: 299938 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.3130. Min Act: -0.0000

Data Index: 1274479 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 2.9787. Min Range: -2.9787

Max Act: 2.4457. Min Act: -0.0000

Data Index: 1264011 (C4 (Web Text))

Max Activating Token Index: 173