Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 34 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7843. Min Act: -0.0002

Data Index: 801703 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7525. Min Act: -0.0003

Data Index: 1332569 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7398. Min Act: -0.0003

Data Index: 661489 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7147. Min Act: -0.0002

Data Index: 881479 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7119. Min Act: -0.0002

Data Index: 1341597 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7296. Min Act: -0.0002

Data Index: 1048704 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7064. Min Act: -0.0002

Data Index: 635476 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6882. Min Act: -0.0002

Data Index: 1016599 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7023. Min Act: -0.0003

Data Index: 1225838 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6883. Min Act: -0.0002

Data Index: 759966 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6804. Min Act: -0.0002

Data Index: 1318919 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6701. Min Act: -0.0002

Data Index: 1085272 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6852. Min Act: -0.0002

Data Index: 649226 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6648. Min Act: -0.0002

Data Index: 801044 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6650. Min Act: -0.0002

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6571. Min Act: -0.0002

Data Index: 1096838 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6591. Min Act: -0.0002

Data Index: 335450 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6587. Min Act: -0.0002

Data Index: 514274 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6519. Min Act: -0.0002

Data Index: 685303 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6533. Min Act: -0.0002

Data Index: 762352 (C4 (Web Text))

Max Activating Token Index: 139