Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2177 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.8076. Min Act: -0.0001

Data Index: 1140973 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.7506. Min Act: -0.0001

Data Index: 1207710 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1137165 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.7364. Min Act: -0.0001

Data Index: 1079140 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1067525 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.7157. Min Act: -0.0001

Data Index: 636809 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.7116. Min Act: -0.0001

Data Index: 955137 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6782. Min Act: -0.0001

Data Index: 624563 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1335999 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6874. Min Act: -0.0001

Data Index: 516477 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6898. Min Act: -0.0001

Data Index: 1251787 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6822. Min Act: -0.0001

Data Index: 1208248 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6811. Min Act: -0.0001

Data Index: 1220076 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.5872. Min Act: -0.0001

Data Index: 476884 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6468. Min Act: -0.0001

Data Index: 461778 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6636. Min Act: -0.0001

Data Index: 423451 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6511. Min Act: -0.0001

Data Index: 1344234 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6911. Min Act: -0.0001

Data Index: 918898 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6671. Min Act: -0.0001

Data Index: 548999 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.8076. Min Range: -0.8076

Max Act: 0.6681. Min Act: -0.0001

Data Index: 364548 (C4 (Web Text))

Max Activating Token Index: 474