Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1985 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1276428 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0488. Min Act: -0.0001

Data Index: 683726 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0488. Min Act: -0.0002

Data Index: 901547 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0448. Min Act: -0.0002

Data Index: 415178 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0442. Min Act: -0.0001

Data Index: 390543 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0439. Min Act: -0.0001

Data Index: 538686 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1384634 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1184812 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0440. Min Act: -0.0001

Data Index: 961899 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1339260 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1296191 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0419. Min Act: -0.0002

Data Index: 371914 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1426586 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0398. Min Act: -0.0002

Data Index: 263969 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0387. Min Act: -0.0001

Data Index: 678631 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1333266 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1228586 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0408. Min Act: -0.0001

Data Index: 828168 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0396. Min Act: -0.0001

Data Index: 495140 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0443. Min Act: -0.0001

Data Index: 960280 (C4 (Web Text))

Max Activating Token Index: 967