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

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

Neuron 1355 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: 2.3153. Min Range: -2.3153

Max Act: 2.3153. Min Act: -0.0000

Data Index: 1489634 (Python Code)

Max Activating Token Index: 73

Text #1

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.9631. Min Act: -0.0000

Data Index: 494642 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.8800. Min Act: -0.0000

Data Index: 1423676 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1466613 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.5995. Min Act: -0.0000

Data Index: 1643355 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.5029. Min Act: -0.0000

Data Index: 1482542 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.4853. Min Act: -0.0000

Data Index: 1589437 (Python Code)

Max Activating Token Index: 868

Text #7

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.5117. Min Act: -0.0000

Data Index: 1433430 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.5550. Min Act: -0.0000

Data Index: 1369721 (Python Code)

Max Activating Token Index: 104

Text #9

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.5320. Min Act: -0.0000

Data Index: 1403538 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1408277 (Python Code)

Max Activating Token Index: 401

Text #11

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.4239. Min Act: -0.0000

Data Index: 1483581 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.4606. Min Act: -0.0000

Data Index: 644505 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1644754 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1533294 (Python Code)

Max Activating Token Index: 449

Text #15

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1521504 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1387361 (Python Code)

Max Activating Token Index: 318

Text #17

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.2782. Min Act: -0.0000

Data Index: 1642906 (Python Code)

Max Activating Token Index: 982

Text #18

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.1985. Min Act: -0.0000

Data Index: 1443516 (Python Code)

Max Activating Token Index: 367

Text #19

Max Range: 2.3153. Min Range: -2.3153

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1456469 (Python Code)

Max Activating Token Index: 551