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

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

Neuron 753 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3211. Min Range: -2.3211

Max Act: 2.3211. Min Act: -0.0000

Data Index: 438756 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 2.3211. Min Range: -2.3211

Max Act: 2.2322. Min Act: -0.0000

Data Index: 109225 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 2.3211. Min Range: -2.3211

Max Act: 2.2000. Min Act: -0.0000

Data Index: 123704 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.7540. Min Act: -0.0000

Data Index: 668071 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.8904. Min Act: -0.0000

Data Index: 368150 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1226013 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.7426. Min Act: -0.0000

Data Index: 819749 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.6185. Min Act: -0.0000

Data Index: 141187 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.5965. Min Act: -0.0000

Data Index: 353777 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.7345. Min Act: -0.0000

Data Index: 447424 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.6250. Min Act: -0.0000

Data Index: 994780 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.6126. Min Act: -0.0000

Data Index: 745448 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1166052 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.5871. Min Act: -0.0000

Data Index: 596399 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.4999. Min Act: -0.0000

Data Index: 228876 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.5854. Min Act: -0.0000

Data Index: 1153481 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.5931. Min Act: -0.0000

Data Index: 99940 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.6838. Min Act: -0.0000

Data Index: 886445 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.5834. Min Act: -0.0000

Data Index: 451650 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 2.3211. Min Range: -2.3211

Max Act: 1.5728. Min Act: -0.0000

Data Index: 600012 (C4 (Web Text))

Max Activating Token Index: 719