Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3195 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0001

Data Index: 813142 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1535040 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1461104 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0452. Min Act: -0.0002

Data Index: 145926 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0433. Min Act: -0.0002

Data Index: 187334 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1581237 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1393168 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1519651 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1640634 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1424764 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1201389 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1638436 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1388704 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1481434 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1639676 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1578552 (Python Code)

Max Activating Token Index: 395

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1274749 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1407342 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1459565 (Python Code)

Max Activating Token Index: 433

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1436012 (Python Code)

Max Activating Token Index: 862