Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1394 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1319798 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: -0.0006

Data Index: 230710 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0143. Min Act: -0.0006

Data Index: 793867 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0141. Min Act: -0.0005

Data Index: 239664 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0138. Min Act: -0.0005

Data Index: 807271 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0134. Min Act: -0.0006

Data Index: 937672 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0136. Min Act: -0.0005

Data Index: 691322 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0136. Min Act: -0.0006

Data Index: 915386 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0135. Min Act: -0.0006

Data Index: 700977 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0006

Data Index: 769876 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0006

Data Index: 431694 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1019375 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1050842 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0131. Min Act: -0.0006

Data Index: 588744 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0131. Min Act: -0.0006

Data Index: 480445 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0131. Min Act: -0.0006

Data Index: 141686 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0005

Data Index: 564528 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0006

Data Index: 463600 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0006

Data Index: 444014 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1099843 (C4 (Web Text))

Max Activating Token Index: 200