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

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

Neuron 47 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.6284. Min Act: -0.0000

Data Index: 1470792 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.4560. Min Act: -0.0000

Data Index: 1611892 (Python Code)

Max Activating Token Index: 724

Text #2

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.2874. Min Act: -0.0001

Data Index: 1611830 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1404230 (Python Code)

Max Activating Token Index: 375

Text #4

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1365423 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1643326 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1451704 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 1.6284. Min Range: -1.6284

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1480890 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1637876 (Python Code)

Max Activating Token Index: 507

Text #9

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1588636 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1451838 (Python Code)

Max Activating Token Index: 897

Text #11

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1485026 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1487135 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1448622 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1608291 (Python Code)

Max Activating Token Index: 847

Text #15

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1541717 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1429056 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1577024 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1529482 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 1.6284. Min Range: -1.6284

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1490507 (Python Code)

Max Activating Token Index: 232