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

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

Neuron 3485 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6698. Min Range: -7.6698

Max Act: 7.6698. Min Act: -0.0001

Data Index: 1008572 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 7.6698. Min Range: -7.6698

Max Act: 7.5899. Min Act: -0.0001

Data Index: 1238354 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 7.6698. Min Range: -7.6698

Max Act: 7.0406. Min Act: -0.0001

Data Index: 348831 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 7.6698. Min Range: -7.6698

Max Act: 7.0338. Min Act: -0.0001

Data Index: 700942 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.8394. Min Act: -0.0001

Data Index: 625917 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.9905. Min Act: -0.0001

Data Index: 591159 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 7.6698. Min Range: -7.6698

Max Act: 7.1693. Min Act: -0.0001

Data Index: 1022674 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 7.6698. Min Range: -7.6698

Max Act: 7.1340. Min Act: -0.0001

Data Index: 1355239 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.4154. Min Act: -0.0001

Data Index: 298909 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.8746. Min Act: -0.0001

Data Index: 800009 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.8139. Min Act: -0.0001

Data Index: 1025059 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.1023. Min Act: -0.0001

Data Index: 417206 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.1928. Min Act: -0.0001

Data Index: 1063102 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.6878. Min Act: -0.0001

Data Index: 934181 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.4854. Min Act: -0.0001

Data Index: 822856 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.6650. Min Act: -0.0001

Data Index: 78530 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.8319. Min Act: -0.0001

Data Index: 313548 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 7.6698. Min Range: -7.6698

Max Act: 7.1639. Min Act: -0.0001

Data Index: 970034 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.6786. Min Act: -0.0001

Data Index: 71770 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 7.6698. Min Range: -7.6698

Max Act: 6.6158. Min Act: -0.0001

Data Index: 1346781 (C4 (Web Text))

Max Activating Token Index: 786