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

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

Neuron 4362 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: 0.9405. Min Range: -0.9405

Max Act: 0.9219. Min Act: -0.0001

Data Index: 55382 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8748. Min Act: -0.0001

Data Index: 1129298 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.9405. Min Act: -0.0001

Data Index: 888697 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.9178. Min Act: -0.0001

Data Index: 909719 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.9358. Min Act: -0.0001

Data Index: 532796 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8404. Min Act: -0.0001

Data Index: 1107075 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8825. Min Act: -0.0001

Data Index: 919879 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8763. Min Act: -0.0001

Data Index: 1307740 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7384. Min Act: -0.0001

Data Index: 1303887 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8171. Min Act: -0.0001

Data Index: 403194 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7328. Min Act: -0.0001

Data Index: 1143147 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1158472 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8722. Min Act: -0.0001

Data Index: 307827 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8715. Min Act: -0.0001

Data Index: 663233 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7620. Min Act: -0.0001

Data Index: 206570 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.7790. Min Act: -0.0001

Data Index: 771404 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8309. Min Act: -0.0001

Data Index: 1023499 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1246880 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6843. Min Act: -0.0001

Data Index: 465858 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.9405. Min Range: -0.9405

Max Act: 0.6912. Min Act: -0.0001

Data Index: 1065190 (C4 (Web Text))

Max Activating Token Index: 693