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

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

Neuron 3875 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: 2.0802. Min Range: -2.0802

Max Act: 2.0802. Min Act: -0.0000

Data Index: 407623 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 2.0802. Min Range: -2.0802

Max Act: 2.0121. Min Act: -0.0000

Data Index: 1238936 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 2.0802. Min Range: -2.0802

Max Act: 2.0100. Min Act: -0.0000

Data Index: 738372 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.9722. Min Act: -0.0000

Data Index: 924392 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.8366. Min Act: -0.0000

Data Index: 1260450 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.8808. Min Act: -0.0000

Data Index: 381967 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.7621. Min Act: -0.0000

Data Index: 442136 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1299256 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.8088. Min Act: -0.0000

Data Index: 42909 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.8171. Min Act: -0.0000

Data Index: 639775 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.7983. Min Act: -0.0000

Data Index: 165513 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.6524. Min Act: -0.0000

Data Index: 1202155 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.6513. Min Act: -0.0000

Data Index: 1032191 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.6482. Min Act: -0.0000

Data Index: 148198 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.7256. Min Act: -0.0000

Data Index: 238923 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.6310. Min Act: -0.0000

Data Index: 30220 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.6211. Min Act: -0.0000

Data Index: 786890 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.8781. Min Act: -0.0000

Data Index: 24670 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.8787. Min Act: -0.0000

Data Index: 584255 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 2.0802. Min Range: -2.0802

Max Act: 1.6917. Min Act: -0.0000

Data Index: 216407 (C4 (Web Text))

Max Activating Token Index: 442