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

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

Neuron 1685 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: 1.1805. Min Range: -1.1805

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1419959 (Python Code)

Max Activating Token Index: 529

Text #1

Max Range: 1.1805. Min Range: -1.1805

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1551677 (Python Code)

Max Activating Token Index: 83

Text #2

Max Range: 1.1805. Min Range: -1.1805

Max Act: 1.1452. Min Act: -0.0000

Data Index: 309398 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.1805. Min Range: -1.1805

Max Act: 1.0384. Min Act: -0.0000

Data Index: 834372 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.1805. Min Range: -1.1805

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1457158 (Python Code)

Max Activating Token Index: 460

Text #5

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1598379 (Python Code)

Max Activating Token Index: 690

Text #6

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1362647 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8692. Min Act: -0.0000

Data Index: 632717 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1324368 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8790. Min Act: -0.0000

Data Index: 186552 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.1805. Min Range: -1.1805

Max Act: 1.0318. Min Act: -0.0000

Data Index: 462690 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8091. Min Act: -0.0000

Data Index: 31752 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8398. Min Act: -0.0000

Data Index: 556527 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.9347. Min Act: -0.0000

Data Index: 865942 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.7610. Min Act: -0.0000

Data Index: 796867 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1371483 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1543704 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8965. Min Act: -0.0000

Data Index: 387757 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.6371. Min Act: -0.0000

Data Index: 836014 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.1805. Min Range: -1.1805

Max Act: 0.8038. Min Act: -0.0000

Data Index: 378814 (C4 (Web Text))

Max Activating Token Index: 652