Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 240 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0003

Data Index: 205510 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0426. Min Act: -0.0003

Data Index: 124215 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0406. Min Act: -0.0003

Data Index: 350253 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0395. Min Act: -0.0003

Data Index: 217098 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0393. Min Act: -0.0003

Data Index: 448769 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1275472 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0389. Min Act: -0.0003

Data Index: 523749 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0378. Min Act: -0.0003

Data Index: 995266 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0377. Min Act: -0.0003

Data Index: 624738 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0371. Min Act: -0.0003

Data Index: 720461 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0368. Min Act: -0.0003

Data Index: 516331 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0369. Min Act: -0.0003

Data Index: 246919 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0368. Min Act: -0.0003

Data Index: 603033 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0360. Min Act: -0.0003

Data Index: 934850 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0369. Min Act: -0.0004

Data Index: 445432 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1194535 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0367. Min Act: -0.0003

Data Index: 703840 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1119970 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0359. Min Act: -0.0003

Data Index: 294367 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0354. Min Act: -0.0003

Data Index: 924594 (C4 (Web Text))

Max Activating Token Index: 716