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

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

Neuron 2441 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: 0.7574. Min Range: -0.7574

Max Act: 0.7574. Min Act: -0.0002

Data Index: 540096 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7391. Min Act: -0.0002

Data Index: 79634 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7162. Min Act: -0.0002

Data Index: 616789 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7206. Min Act: -0.0002

Data Index: 1022640 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7179. Min Act: -0.0002

Data Index: 737375 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7208. Min Act: -0.0002

Data Index: 546865 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7148. Min Act: -0.0002

Data Index: 297915 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7177. Min Act: -0.0002

Data Index: 504352 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6959. Min Act: -0.0002

Data Index: 546930 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7083. Min Act: -0.0002

Data Index: 42581 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7070. Min Act: -0.0002

Data Index: 833648 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6870. Min Act: -0.0002

Data Index: 1291766 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7028. Min Act: -0.0002

Data Index: 222870 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6944. Min Act: -0.0002

Data Index: 237710 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6861. Min Act: -0.0002

Data Index: 629261 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6920. Min Act: -0.0002

Data Index: 906863 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6752. Min Act: -0.0002

Data Index: 1184613 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6897. Min Act: -0.0002

Data Index: 631605 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6874. Min Act: -0.0002

Data Index: 1296231 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6667. Min Act: -0.0002

Data Index: 843016 (C4 (Web Text))

Max Activating Token Index: 456