Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 322 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7884. Min Act: -0.0001

Data Index: 126468 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7758. Min Act: -0.0001

Data Index: 945084 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6014. Min Act: -0.0001

Data Index: 206219 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6069. Min Act: -0.0001

Data Index: 787745 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6994. Min Act: -0.0001

Data Index: 1210983 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6258. Min Act: -0.0001

Data Index: 982010 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6850. Min Act: -0.0001

Data Index: 1093031 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6246. Min Act: -0.0001

Data Index: 1341420 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6058. Min Act: -0.0001

Data Index: 710939 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6623. Min Act: -0.0001

Data Index: 1069701 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5815. Min Act: -0.0001

Data Index: 974637 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5038. Min Act: -0.0001

Data Index: 268151 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5368. Min Act: -0.0001

Data Index: 1255762 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5977. Min Act: -0.0001

Data Index: 362747 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5728. Min Act: -0.0001

Data Index: 1196579 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5250. Min Act: -0.0001

Data Index: 27497 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.4961. Min Act: -0.0001

Data Index: 1309355 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5871. Min Act: -0.0001

Data Index: 1039664 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1084297 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5753. Min Act: -0.0001

Data Index: 205221 (C4 (Web Text))

Max Activating Token Index: 488