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

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

Neuron 545 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.3353. Min Act: -0.0000

Data Index: 1427623 (Python Code)

Max Activating Token Index: 572

Text #1

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.2141. Min Act: -0.0000

Data Index: 710953 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.2083. Min Act: 0.0000

Data Index: 1425292 (Python Code)

Max Activating Token Index: 371

Text #3

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0429. Min Act: -0.0000

Data Index: 1524113 (Python Code)

Max Activating Token Index: 634

Text #4

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.9626. Min Act: -0.0000

Data Index: 335931 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.8607. Min Act: -0.0000

Data Index: 368062 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.6553. Min Act: -0.0000

Data Index: 884125 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0783. Min Act: -0.0000

Data Index: 1629827 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.7810. Min Act: -0.0000

Data Index: 927105 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.5420. Min Act: -0.0000

Data Index: 1419705 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.6680. Min Act: -0.0000

Data Index: 508512 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.7678. Min Act: -0.0000

Data Index: 1537478 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.6333. Min Act: -0.0000

Data Index: 1486053 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.4593. Min Act: -0.0000

Data Index: 1588773 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.3361. Min Act: -0.0000

Data Index: 1601024 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.6700. Min Act: -0.0000

Data Index: 1382222 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.3918. Min Act: -0.0000

Data Index: 1480042 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.6177. Min Act: -0.0000

Data Index: 1611115 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.4303. Min Act: -0.0000

Data Index: 1417458 (Python Code)

Max Activating Token Index: 416

Text #19

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.3002. Min Act: -0.0000

Data Index: 1480375 (Python Code)

Max Activating Token Index: 11