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

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

Neuron 5774 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: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0001

Data Index: 724537 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0414. Min Act: -0.0001

Data Index: 669363 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0423. Min Act: -0.0001

Data Index: 230005 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0400. Min Act: -0.0001

Data Index: 539840 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0401. Min Act: -0.0001

Data Index: 476644 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1137777 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0403. Min Act: -0.0001

Data Index: 323771 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0383. Min Act: -0.0001

Data Index: 728707 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0370. Min Act: -0.0001

Data Index: 874769 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0364. Min Act: -0.0001

Data Index: 33408 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0357. Min Act: -0.0001

Data Index: 275268 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0354. Min Act: -0.0001

Data Index: 212075 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0350. Min Act: -0.0001

Data Index: 625094 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1223035 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0348. Min Act: -0.0001

Data Index: 581513 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0348. Min Act: -0.0001

Data Index: 551118 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0343. Min Act: -0.0001

Data Index: 650857 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1197910 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0333. Min Act: -0.0001

Data Index: 40719 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0341. Min Act: -0.0001

Data Index: 913761 (C4 (Web Text))

Max Activating Token Index: 891