Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 502 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0003

Data Index: 611845 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0555. Min Act: -0.0003

Data Index: 518521 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0543. Min Act: -0.0003

Data Index: 754348 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0499. Min Act: -0.0003

Data Index: 403876 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1302980 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0493. Min Act: -0.0003

Data Index: 151343 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0494. Min Act: -0.0003

Data Index: 457566 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1212963 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0446. Min Act: -0.0003

Data Index: 219793 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0452. Min Act: -0.0003

Data Index: 88010 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0424. Min Act: -0.0003

Data Index: 427685 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0430. Min Act: -0.0003

Data Index: 207994 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1270232 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0426. Min Act: -0.0001

Data Index: 463590 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0427. Min Act: -0.0003

Data Index: 391689 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1068204 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0423. Min Act: -0.0003

Data Index: 206000 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0420. Min Act: -0.0003

Data Index: 679740 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0414. Min Act: -0.0003

Data Index: 501564 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0413. Min Act: -0.0003

Data Index: 766461 (C4 (Web Text))

Max Activating Token Index: 434