Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1364484 (Python Code)

Max Activating Token Index: 868

Text #1

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1415761 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1394740 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1363099 (Python Code)

Max Activating Token Index: 465

Text #4

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.0747. Min Act: -0.0000

Data Index: 1469446 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1599931 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1525725 (Python Code)

Max Activating Token Index: 201

Text #7

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1644187 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1414287 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1563270 (Python Code)

Max Activating Token Index: 846

Text #10

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1496795 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1456433 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1533259 (Python Code)

Max Activating Token Index: 843

Text #13

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1476806 (Python Code)

Max Activating Token Index: 705

Text #14

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1478017 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1634492 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1448166 (Python Code)

Max Activating Token Index: 945

Text #17

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1529591 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1641274 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1367718 (Python Code)

Max Activating Token Index: 464