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

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

Neuron 4905 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.7685. Min Act: -0.0001

Data Index: 769646 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.6408. Min Act: -0.0001

Data Index: 73006 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4990. Min Act: -0.0000

Data Index: 33939 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5630. Min Act: -0.0000

Data Index: 29482 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5657. Min Act: -0.0001

Data Index: 157525 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5047. Min Act: -0.0001

Data Index: 960018 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4676. Min Act: -0.0001

Data Index: 870008 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5522. Min Act: -0.0001

Data Index: 681730 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5000. Min Act: -0.0001

Data Index: 68177 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5292. Min Act: -0.0001

Data Index: 252561 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4691. Min Act: -0.0001

Data Index: 334210 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4700. Min Act: -0.0000

Data Index: 163641 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5198. Min Act: -0.0000

Data Index: 181306 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4670. Min Act: -0.0001

Data Index: 304012 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.5048. Min Act: -0.0001

Data Index: 206257 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4578. Min Act: -0.0000

Data Index: 36952 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4127. Min Act: -0.0001

Data Index: 1195498 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4927. Min Act: -0.0001

Data Index: 348394 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1166185 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.7685. Min Range: -0.7685

Max Act: 0.4987. Min Act: -0.0001

Data Index: 113826 (C4 (Web Text))

Max Activating Token Index: 809