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

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

Neuron 2468 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9268. Min Range: -6.9268

Max Act: 6.9268. Min Act: -0.0000

Data Index: 1574419 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 6.9268. Min Range: -6.9268

Max Act: 6.4813. Min Act: -0.0000

Data Index: 871213 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.5472. Min Act: -0.0000

Data Index: 273516 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.4867. Min Act: -0.0000

Data Index: 1348692 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.6503. Min Act: -0.0000

Data Index: 1515287 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.5120. Min Act: -0.0000

Data Index: 113351 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.2348. Min Act: -0.0000

Data Index: 1540480 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.3363. Min Act: -0.0000

Data Index: 1401965 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.4284. Min Act: -0.0000

Data Index: 760895 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.0209. Min Act: -0.0000

Data Index: 1533676 (Python Code)

Max Activating Token Index: 465

Text #10

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.1903. Min Act: -0.0000

Data Index: 910785 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.9795. Min Act: 0.0000

Data Index: 1499534 (Python Code)

Max Activating Token Index: 603

Text #12

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.9698. Min Act: -0.0000

Data Index: 1470620 (Python Code)

Max Activating Token Index: 632

Text #13

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.9453. Min Act: -0.0000

Data Index: 773201 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.9299. Min Act: -0.0000

Data Index: 991850 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 6.9268. Min Range: -6.9268

Max Act: 5.0384. Min Act: -0.0000

Data Index: 1596475 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.8526. Min Act: -0.0000

Data Index: 86209 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.8453. Min Act: -0.0000

Data Index: 100447 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.6434. Min Act: -0.0000

Data Index: 935274 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 6.9268. Min Range: -6.9268

Max Act: 4.9739. Min Act: -0.0000

Data Index: 1505350 (Python Code)

Max Activating Token Index: 82