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

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

Neuron 4528 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1608147 (Python Code)

Max Activating Token Index: 760

Text #1

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1407702 (Python Code)

Max Activating Token Index: 105

Text #2

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.1139. Min Act: -0.0001

Data Index: 1652092 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1364659 (Python Code)

Max Activating Token Index: 645

Text #4

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1400156 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 1.3635. Min Range: -1.3635

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1549238 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1373991 (Python Code)

Max Activating Token Index: 861

Text #7

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1424689 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1527621 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1377142 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1585912 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1637468 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1416069 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1628431 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1368359 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1505025 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1391802 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1645260 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1614375 (Python Code)

Max Activating Token Index: 456

Text #19

Max Range: 1.3635. Min Range: -1.3635

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1383961 (Python Code)

Max Activating Token Index: 119