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

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

Neuron 1825 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: 0.0949. Min Range: -0.0949

Max Act: 0.0949. Min Act: -0.0002

Data Index: 75894 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1304711 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1097942 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1422556 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0880. Min Act: -0.0002

Data Index: 603934 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0852. Min Act: -0.0002

Data Index: 927735 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1444593 (Python Code)

Max Activating Token Index: 66

Text #8

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0820. Min Act: -0.0002

Data Index: 321380 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0811. Min Act: -0.0002

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1163754 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0790. Min Act: -0.0002

Data Index: 921235 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0800. Min Act: -0.0002

Data Index: 634135 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0787. Min Act: -0.0002

Data Index: 791102 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1325258 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0763. Min Act: -0.0002

Data Index: 964689 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1461133 (Python Code)

Max Activating Token Index: 590

Text #17

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0743. Min Act: -0.0002

Data Index: 143746 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0734. Min Act: -0.0002

Data Index: 417379 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0747. Min Act: -0.0002

Data Index: 361254 (C4 (Web Text))

Max Activating Token Index: 565