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

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

Neuron 4459 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1308742 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0974. Min Act: -0.0001

Data Index: 249786 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0954. Min Act: -0.0001

Data Index: 104605 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0874. Min Act: -0.0001

Data Index: 77673 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0833. Min Act: -0.0001

Data Index: 737689 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0726. Min Act: -0.0001

Data Index: 864603 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0803. Min Act: -0.0001

Data Index: 840970 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0791. Min Act: -0.0001

Data Index: 543565 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0710. Min Act: -0.0001

Data Index: 75252 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0822. Min Act: -0.0001

Data Index: 188979 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0761. Min Act: -0.0001

Data Index: 20924 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0790. Min Act: -0.0001

Data Index: 487162 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1356045 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0690. Min Act: -0.0001

Data Index: 381064 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0740. Min Act: -0.0001

Data Index: 238805 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1264645 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0742. Min Act: -0.0001

Data Index: 167397 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1190038 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0649. Min Act: -0.0001

Data Index: 554719 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0807. Min Act: -0.0001

Data Index: 896040 (C4 (Web Text))

Max Activating Token Index: 350