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

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

Neuron 3854 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: 1.0849. Min Range: -1.0849

Max Act: 1.0849. Min Act: -0.0000

Data Index: 76795 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9568. Min Act: -0.0001

Data Index: 491880 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9889. Min Act: -0.0001

Data Index: 931973 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9572. Min Act: -0.0001

Data Index: 1302740 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8661. Min Act: -0.0001

Data Index: 95085 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9089. Min Act: -0.0001

Data Index: 1159098 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8945. Min Act: -0.0001

Data Index: 106348 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9795. Min Act: -0.0001

Data Index: 161834 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9818. Min Act: -0.0001

Data Index: 761961 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9156. Min Act: -0.0001

Data Index: 1267900 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8881. Min Act: -0.0001

Data Index: 27681 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8131. Min Act: -0.0001

Data Index: 365459 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9037. Min Act: -0.0001

Data Index: 156768 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9134. Min Act: -0.0001

Data Index: 494688 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7980. Min Act: -0.0001

Data Index: 580517 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7796. Min Act: -0.0001

Data Index: 890204 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7377. Min Act: -0.0001

Data Index: 940094 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7302. Min Act: -0.0001

Data Index: 821698 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1104217 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7294. Min Act: -0.0001

Data Index: 742232 (C4 (Web Text))

Max Activating Token Index: 347