Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9917. Min Act: -0.0000

Data Index: 1575271 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9456. Min Act: -0.0001

Data Index: 1531358 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9194. Min Act: -0.0001

Data Index: 1510299 (Python Code)

Max Activating Token Index: 782

Text #3

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.8317. Min Act: -0.0001

Data Index: 1462086 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9521. Min Act: -0.0001

Data Index: 1451827 (Python Code)

Max Activating Token Index: 343

Text #5

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9486. Min Act: -0.0001

Data Index: 1650283 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9884. Min Act: -0.0001

Data Index: 1383952 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.8953. Min Act: -0.0001

Data Index: 1463919 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9675. Min Act: -0.0001

Data Index: 1604656 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7962. Min Act: -0.0001

Data Index: 1519474 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.8220. Min Act: -0.0000

Data Index: 1619024 (Python Code)

Max Activating Token Index: 544

Text #11

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7613. Min Act: -0.0001

Data Index: 1387532 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7686. Min Act: -0.0001

Data Index: 1471962 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7662. Min Act: -0.0001

Data Index: 1635962 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7390. Min Act: -0.0001

Data Index: 1523063 (Python Code)

Max Activating Token Index: 101

Text #15

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.8408. Min Act: -0.0001

Data Index: 1510489 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7696. Min Act: -0.0000

Data Index: 1554411 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7674. Min Act: -0.0001

Data Index: 1566064 (Python Code)

Max Activating Token Index: 801

Text #18

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7562. Min Act: -0.0001

Data Index: 1611738 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.6583. Min Act: -0.0001

Data Index: 1645693 (Python Code)

Max Activating Token Index: 240