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

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

Neuron 5 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: 2.4770. Min Range: -2.4770

Max Act: 2.4770. Min Act: -0.0000

Data Index: 1484434 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.4109. Min Act: -0.0000

Data Index: 1600568 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.3893. Min Act: -0.0000

Data Index: 1608235 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1607630 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.0361. Min Act: -0.0000

Data Index: 1379219 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.1273. Min Act: -0.0000

Data Index: 1390267 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1560608 (Python Code)

Max Activating Token Index: 208

Text #7

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.0625. Min Act: -0.0000

Data Index: 1430737 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.0314. Min Act: -0.0000

Data Index: 621995 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1632595 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.8631. Min Act: -0.0000

Data Index: 1539779 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1548177 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.9416. Min Act: -0.0000

Data Index: 1400756 (Python Code)

Max Activating Token Index: 684

Text #13

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.0443. Min Act: -0.0000

Data Index: 1367820 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.9315. Min Act: -0.0000

Data Index: 1520385 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.9204. Min Act: -0.0000

Data Index: 339325 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 2.4770. Min Range: -2.4770

Max Act: 2.0641. Min Act: -0.0000

Data Index: 1635991 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.8681. Min Act: -0.0000

Data Index: 614533 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.8493. Min Act: -0.0000

Data Index: 1423248 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 2.4770. Min Range: -2.4770

Max Act: 1.8298. Min Act: -0.0000

Data Index: 1454788 (Python Code)

Max Activating Token Index: 647