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

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

Neuron 3575 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: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1638442 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0374. Min Act: -0.0001

Data Index: 556154 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0366. Min Act: -0.0001

Data Index: 417852 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1389543 (Python Code)

Max Activating Token Index: 533

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0370. Min Act: -0.0001

Data Index: 796986 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0361. Min Act: -0.0001

Data Index: 623634 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1212803 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0363. Min Act: -0.0001

Data Index: 579237 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1246646 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0365. Min Act: -0.0001

Data Index: 424950 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1544236 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0366. Min Act: -0.0001

Data Index: 773571 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1565606 (Python Code)

Max Activating Token Index: 921

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0361. Min Act: -0.0001

Data Index: 183389 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0354. Min Act: -0.0001

Data Index: 391273 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1461134 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1120088 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0362. Min Act: -0.0002

Data Index: 168614 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0358. Min Act: -0.0001

Data Index: 501986 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0353. Min Act: -0.0001

Data Index: 386595 (C4 (Web Text))

Max Activating Token Index: 490