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

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

Neuron 721 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: 1.3008. Min Range: -1.3008

Max Act: 1.3008. Min Act: -0.0000

Data Index: 314536 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.2604. Min Act: -0.0001

Data Index: 1640889 (Python Code)

Max Activating Token Index: 376

Text #2

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.1543. Min Act: -0.0001

Data Index: 384814 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0873. Min Act: -0.0001

Data Index: 545652 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0880. Min Act: -0.0001

Data Index: 1188516 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0931. Min Act: -0.0001

Data Index: 685230 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.1192. Min Act: -0.0001

Data Index: 253752 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.1256. Min Act: -0.0000

Data Index: 68730 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.1006. Min Act: -0.0001

Data Index: 1023545 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9206. Min Act: -0.0001

Data Index: 418678 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9935. Min Act: -0.0001

Data Index: 940881 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0103. Min Act: -0.0001

Data Index: 302048 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0770. Min Act: -0.0001

Data Index: 479739 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0360. Min Act: -0.0001

Data Index: 951916 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0353. Min Act: -0.0001

Data Index: 1283646 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0010. Min Act: -0.0001

Data Index: 1328385 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1041609 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9917. Min Act: -0.0001

Data Index: 783448 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0038. Min Act: -0.0001

Data Index: 292461 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9742. Min Act: -0.0001

Data Index: 357127 (C4 (Web Text))

Max Activating Token Index: 239