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

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

Neuron 2474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0462. Min Range: -1.0462

Max Act: 1.0153. Min Act: -0.0000

Data Index: 864063 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.0462. Min Range: -1.0462

Max Act: 1.0462. Min Act: -0.0000

Data Index: 364972 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7858. Min Act: -0.0001

Data Index: 568112 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1162571 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7180. Min Act: -0.0001

Data Index: 1012052 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7095. Min Act: -0.0001

Data Index: 85620 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1337550 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6219. Min Act: -0.0000

Data Index: 809645 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7322. Min Act: -0.0001

Data Index: 379543 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.5707. Min Act: -0.0000

Data Index: 958254 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.5681. Min Act: -0.0000

Data Index: 346743 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6090. Min Act: 0.0000

Data Index: 131207 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6049. Min Act: -0.0001

Data Index: 409567 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.5615. Min Act: -0.0000

Data Index: 878460 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.5801. Min Act: -0.0001

Data Index: 1217917 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1177930 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6107. Min Act: -0.0000

Data Index: 552363 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6075. Min Act: -0.0001

Data Index: 978667 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.5899. Min Act: -0.0000

Data Index: 775522 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1287572 (C4 (Web Text))

Max Activating Token Index: 77