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

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

Neuron 3307 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2176. Min Act: -0.0001

Data Index: 527629 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1357163 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2022. Min Act: -0.0001

Data Index: 418110 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1329484 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1937. Min Act: -0.0001

Data Index: 435226 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1802. Min Act: -0.0001

Data Index: 19061 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2084. Min Act: -0.0001

Data Index: 54119 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1748. Min Act: -0.0001

Data Index: 238112 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1854. Min Act: -0.0001

Data Index: 13352 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1869. Min Act: -0.0001

Data Index: 606662 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1276759 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1802. Min Act: -0.0001

Data Index: 996252 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1690. Min Act: -0.0001

Data Index: 25701 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1618. Min Act: -0.0001

Data Index: 274932 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1483. Min Act: -0.0001

Data Index: 568608 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1750. Min Act: -0.0001

Data Index: 1085880 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1145787 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1405048 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1737. Min Act: -0.0001

Data Index: 1229770 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1653. Min Act: -0.0001

Data Index: 951783 (C4 (Web Text))

Max Activating Token Index: 520