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

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

Neuron 3367 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.9285. Min Act: -0.0001

Data Index: 1045500 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.7804. Min Act: -0.0002

Data Index: 616293 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.7423. Min Act: -0.0001

Data Index: 103601 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.7577. Min Act: -0.0001

Data Index: 667808 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5910. Min Act: -0.0001

Data Index: 590836 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.7274. Min Act: -0.0001

Data Index: 460652 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.6995. Min Act: -0.0001

Data Index: 145474 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.6880. Min Act: -0.0001

Data Index: 1078556 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5287. Min Act: -0.0001

Data Index: 295709 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5968. Min Act: -0.0001

Data Index: 1245572 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.4994. Min Act: -0.0001

Data Index: 215527 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.6766. Min Act: -0.0001

Data Index: 252998 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.6463. Min Act: -0.0001

Data Index: 1087814 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5433. Min Act: -0.0001

Data Index: 248974 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5537. Min Act: -0.0001

Data Index: 68153 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5181. Min Act: -0.0001

Data Index: 303431 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5323. Min Act: -0.0001

Data Index: 23390 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.4730. Min Act: -0.0001

Data Index: 676230 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5950. Min Act: -0.0001

Data Index: 682938 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 2.9285. Min Range: -2.9285

Max Act: 2.5150. Min Act: -0.0001

Data Index: 71147 (C4 (Web Text))

Max Activating Token Index: 589