Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5864 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0001

Data Index: 450806 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1446619 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1112576 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0120. Min Act: -0.0001

Data Index: 194529 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1417003 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0118. Min Act: -0.0001

Data Index: 1645611 (Python Code)

Max Activating Token Index: 581

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0001

Data Index: 1033888 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0001

Data Index: 755722 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 289473 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1376192 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1414869 (Python Code)

Max Activating Token Index: 556

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0001

Data Index: 253419 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0001

Data Index: 233336 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0001

Data Index: 129420 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0001

Data Index: 907428 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1623057 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0001

Data Index: 1413155 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0001

Data Index: 1168884 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0001

Data Index: 155493 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0001

Data Index: 704249 (C4 (Web Text))

Max Activating Token Index: 32