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

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

Neuron 3679 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.6834. Min Act: -0.0000

Data Index: 759213 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.5608. Min Act: -0.0000

Data Index: 653624 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.5668. Min Act: -0.0000

Data Index: 266042 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4500. Min Act: -0.0000

Data Index: 382261 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1074735 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1017413 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4244. Min Act: -0.0000

Data Index: 862229 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4308. Min Act: -0.0000

Data Index: 23666 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3376. Min Act: -0.0000

Data Index: 515341 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3402. Min Act: -0.0000

Data Index: 790540 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4137. Min Act: -0.0000

Data Index: 1121406 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1127595 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4841. Min Act: -0.0000

Data Index: 419452 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2860. Min Act: -0.0000

Data Index: 867835 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1455032 (Python Code)

Max Activating Token Index: 477

Text #15

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2945. Min Act: -0.0000

Data Index: 61535 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.4286. Min Act: -0.0000

Data Index: 348467 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1035324 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1044518 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3209. Min Act: -0.0000

Data Index: 570257 (C4 (Web Text))

Max Activating Token Index: 46