Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1314 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.3285. Min Act: -0.0002

Data Index: 794771 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.3084. Min Act: -0.0002

Data Index: 209242 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.2350. Min Act: -0.0002

Data Index: 205073 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.1946. Min Act: -0.0002

Data Index: 976177 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0889. Min Act: -0.0002

Data Index: 441836 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9913. Min Act: -0.0002

Data Index: 358123 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9910. Min Act: -0.0001

Data Index: 1343505 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0060. Min Act: -0.0002

Data Index: 1150996 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9988. Min Act: -0.0001

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9760. Min Act: -0.0001

Data Index: 1150993 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0252. Min Act: -0.0001

Data Index: 1033333 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9849. Min Act: -0.0002

Data Index: 1131970 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9085. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0507. Min Act: -0.0001

Data Index: 760012 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8217. Min Act: -0.0001

Data Index: 220491 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9088. Min Act: -0.0001

Data Index: 168622 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9021. Min Act: -0.0002

Data Index: 173271 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8908. Min Act: -0.0001

Data Index: 185648 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8392. Min Act: -0.0001

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0140. Min Act: -0.0002

Data Index: 1088892 (C4 (Web Text))

Max Activating Token Index: 724