Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2302 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.1667. Min Act: -0.0001

Data Index: 1637641 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0340. Min Act: -0.0001

Data Index: 1474010 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0253. Min Act: -0.0001

Data Index: 1567634 (Python Code)

Max Activating Token Index: 479

Text #3

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1547846 (Python Code)

Max Activating Token Index: 599

Text #4

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9747. Min Act: -0.0001

Data Index: 1396576 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1650133 (Python Code)

Max Activating Token Index: 898

Text #6

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9132. Min Act: -0.0001

Data Index: 1561690 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9113. Min Act: -0.0001

Data Index: 1582436 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9450. Min Act: -0.0001

Data Index: 1610688 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9140. Min Act: -0.0001

Data Index: 1520043 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9107. Min Act: -0.0001

Data Index: 1427549 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1447294 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8947. Min Act: -0.0001

Data Index: 1487973 (Python Code)

Max Activating Token Index: 596

Text #13

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8805. Min Act: -0.0001

Data Index: 1448149 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1562003 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8633. Min Act: -0.0001

Data Index: 1612174 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8289. Min Act: -0.0001

Data Index: 1570195 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8308. Min Act: -0.0001

Data Index: 1489144 (Python Code)

Max Activating Token Index: 271

Text #18

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8825. Min Act: -0.0001

Data Index: 1453547 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8545. Min Act: -0.0001

Data Index: 1632196 (Python Code)

Max Activating Token Index: 862