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

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

Neuron 1564 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.6236. Min Act: -0.0000

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.6011. Min Act: -0.0000

Data Index: 301100 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1178382 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5865. Min Act: -0.0000

Data Index: 417044 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1037845 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5723. Min Act: -0.0000

Data Index: 962580 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5728. Min Act: 0.0000

Data Index: 1314956 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5307. Min Act: -0.0000

Data Index: 33083 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5589. Min Act: -0.0000

Data Index: 247474 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1136096 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5397. Min Act: -0.0000

Data Index: 5243 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5235. Min Act: -0.0000

Data Index: 600986 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5235. Min Act: -0.0000

Data Index: 900765 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1217877 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1058781 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5300. Min Act: 0.0000

Data Index: 910924 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1098012 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.4972. Min Act: 0.0001

Data Index: 352897 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1069626 (C4 (Web Text))

Max Activating Token Index: 826