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

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

Neuron 2548 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2606. Min Range: -3.2606

Max Act: 3.2606. Min Act: -0.0000

Data Index: 795591 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.7153. Min Act: -0.0000

Data Index: 368196 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.1893. Min Act: -0.0000

Data Index: 887645 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.2776. Min Act: -0.0000

Data Index: 1257352 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.1449. Min Act: -0.0000

Data Index: 555358 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.0487. Min Act: -0.0000

Data Index: 151652 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.0454. Min Act: -0.0000

Data Index: 133659 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.0419. Min Act: -0.0000

Data Index: 776677 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.9122. Min Act: -0.0000

Data Index: 269897 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.0311. Min Act: -0.0000

Data Index: 1456 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.0042. Min Act: -0.0000

Data Index: 1237641 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.8338. Min Act: -0.0000

Data Index: 547888 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 3.2606. Min Range: -3.2606

Max Act: 2.0228. Min Act: -0.0000

Data Index: 220751 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.8995. Min Act: -0.0000

Data Index: 379298 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.8564. Min Act: -0.0000

Data Index: 168839 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.8428. Min Act: -0.0000

Data Index: 1544007 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1253656 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.8174. Min Act: -0.0000

Data Index: 1205974 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1223950 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 3.2606. Min Range: -3.2606

Max Act: 1.6851. Min Act: -0.0000

Data Index: 471234 (C4 (Web Text))

Max Activating Token Index: 600