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

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

Neuron 3355 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: 0.0147. Min Range: -0.0147

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1591410 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0140. Min Act: -0.0001

Data Index: 256653 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0131. Min Act: -0.0001

Data Index: 875839 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1202604 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0133. Min Act: -0.0001

Data Index: 1417057 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0130. Min Act: -0.0001

Data Index: 667286 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1553794 (Python Code)

Max Activating Token Index: 637

Text #7

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1334345 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0126. Min Act: -0.0001

Data Index: 875621 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0124. Min Act: -0.0001

Data Index: 669778 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0123. Min Act: -0.0001

Data Index: 1023694 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1054621 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0123. Min Act: -0.0001

Data Index: 1643434 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0126. Min Act: -0.0001

Data Index: 482370 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0122. Min Act: -0.0001

Data Index: 334632 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0122. Min Act: -0.0001

Data Index: 42987 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1101215 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0117. Min Act: -0.0001

Data Index: 1006464 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0001

Data Index: 709256 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0118. Min Act: -0.0001

Data Index: 41562 (C4 (Web Text))

Max Activating Token Index: 1000