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

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

Neuron 4724 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.6834. Min Act: -0.0000

Data Index: 651571 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 4.1371. Min Range: -4.1371

Max Act: 4.1371. Min Act: -0.0000

Data Index: 409394 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.6538. Min Act: -0.0001

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.3578. Min Act: -0.0001

Data Index: 615453 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.3981. Min Act: -0.0001

Data Index: 235887 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1585. Min Act: -0.0001

Data Index: 1284344 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.3191. Min Act: -0.0000

Data Index: 395173 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.4635. Min Act: -0.0000

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1404. Min Act: -0.0000

Data Index: 1191747 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1388. Min Act: -0.0001

Data Index: 299751 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.3925. Min Act: -0.0001

Data Index: 387068 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 4.1371. Min Range: -4.1371

Max Act: 2.9186. Min Act: -0.0001

Data Index: 607753 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 4.1371. Min Range: -4.1371

Max Act: 2.8594. Min Act: -0.0001

Data Index: 27267 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1617. Min Act: -0.0001

Data Index: 728241 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 4.1371. Min Range: -4.1371

Max Act: 2.9925. Min Act: -0.0001

Data Index: 395525 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1845. Min Act: -0.0001

Data Index: 145999 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1242. Min Act: -0.0001

Data Index: 950595 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1155. Min Act: -0.0001

Data Index: 107993 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.1096. Min Act: -0.0001

Data Index: 126741 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 4.1371. Min Range: -4.1371

Max Act: 3.0045. Min Act: -0.0001

Data Index: 487301 (C4 (Web Text))

Max Activating Token Index: 706