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

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

Neuron 3960 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1445979 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4211. Min Act: -0.0000

Data Index: 573312 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1650690 (Python Code)

Max Activating Token Index: 323

Text #3

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1396732 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1565213 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1463014 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1431593 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1508392 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1642581 (Python Code)

Max Activating Token Index: 985

Text #9

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1555966 (Python Code)

Max Activating Token Index: 267

Text #10

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1493056 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1564278 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1495260 (Python Code)

Max Activating Token Index: 377

Text #13

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1100890 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1605296 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1630601 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1524032 (Python Code)

Max Activating Token Index: 86

Text #17

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1426520 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1542704 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1522616 (Python Code)

Max Activating Token Index: 272