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

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

Neuron 5028 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.7322. Min Act: -0.0000

Data Index: 273795 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.4247. Min Act: -0.0000

Data Index: 452352 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.2073. Min Act: -0.0000

Data Index: 721327 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.2756. Min Act: -0.0000

Data Index: 31750 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.0999. Min Act: -0.0000

Data Index: 591124 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.1769. Min Act: -0.0000

Data Index: 1026349 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.1504. Min Act: -0.0000

Data Index: 148569 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.9202. Min Act: -0.0000

Data Index: 418215 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.9092. Min Act: -0.0000

Data Index: 498913 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.1144. Min Act: -0.0000

Data Index: 184528 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.0982. Min Act: -0.0000

Data Index: 865203 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.9554. Min Act: -0.0000

Data Index: 109694 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.0419. Min Act: -0.0000

Data Index: 381567 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.9908. Min Act: -0.0000

Data Index: 918970 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.8112. Min Act: -0.0000

Data Index: 927978 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.7081. Min Act: -0.0000

Data Index: 1001145 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1194261 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.7253. Min Act: -0.0000

Data Index: 695042 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1177779 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.6872. Min Act: -0.0000

Data Index: 452696 (C4 (Web Text))

Max Activating Token Index: 487