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

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

Neuron 900 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: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0001

Data Index: 903704 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0412. Min Act: -0.0001

Data Index: 449117 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0408. Min Act: -0.0002

Data Index: 384601 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0398. Min Act: -0.0001

Data Index: 601503 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0389. Min Act: -0.0001

Data Index: 297829 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0385. Min Act: -0.0001

Data Index: 747554 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1208002 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0370. Min Act: -0.0001

Data Index: 612001 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0375. Min Act: -0.0001

Data Index: 21980 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0376. Min Act: -0.0001

Data Index: 330361 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0368. Min Act: -0.0001

Data Index: 933629 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0361. Min Act: -0.0001

Data Index: 256211 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0367. Min Act: -0.0001

Data Index: 914839 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0366. Min Act: -0.0001

Data Index: 666598 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0353. Min Act: -0.0001

Data Index: 466624 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0362. Min Act: -0.0001

Data Index: 669490 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0362. Min Act: -0.0001

Data Index: 502538 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0357. Min Act: -0.0001

Data Index: 372712 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0353. Min Act: -0.0001

Data Index: 752115 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0348. Min Act: -0.0001

Data Index: 875093 (C4 (Web Text))

Max Activating Token Index: 879