Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3582 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.3110. Min Range: -5.3110

Max Act: 5.3110. Min Act: -0.0001

Data Index: 938729 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.5516. Min Act: -0.0001

Data Index: 1055812 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.8735. Min Act: -0.0001

Data Index: 1015916 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.2451. Min Act: -0.0001

Data Index: 502361 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.7392. Min Act: -0.0001

Data Index: 942883 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.3087. Min Act: -0.0001

Data Index: 885490 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.4146. Min Act: -0.0001

Data Index: 532067 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.0402. Min Act: -0.0001

Data Index: 1275227 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.9895. Min Act: -0.0001

Data Index: 492686 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.9696. Min Act: -0.0001

Data Index: 898636 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.8061. Min Act: -0.0001

Data Index: 596724 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.7642. Min Act: -0.0001

Data Index: 800570 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.7185. Min Act: -0.0001

Data Index: 136083 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.7090. Min Act: -0.0001

Data Index: 333655 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 5.3110. Min Range: -5.3110

Max Act: 4.0211. Min Act: -0.0001

Data Index: 698994 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.7991. Min Act: -0.0001

Data Index: 179559 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.7738. Min Act: -0.0001

Data Index: 1273984 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.7481. Min Act: -0.0001

Data Index: 530109 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.5653. Min Act: -0.0001

Data Index: 380256 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 5.3110. Min Range: -5.3110

Max Act: 3.5401. Min Act: -0.0001

Data Index: 765445 (C4 (Web Text))

Max Activating Token Index: 227