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

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

Neuron 2076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3361. Min Act: -0.0001

Data Index: 580718 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.1862. Min Act: -0.0000

Data Index: 577569 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0979. Min Act: -0.0000

Data Index: 908786 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1312472 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.9990. Min Act: -0.0001

Data Index: 247093 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.9368. Min Act: -0.0000

Data Index: 493078 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.9625. Min Act: -0.0001

Data Index: 664952 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.9190. Min Act: -0.0001

Data Index: 237304 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1291787 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.8779. Min Act: -0.0001

Data Index: 171366 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.8444. Min Act: -0.0001

Data Index: 138161 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.8556. Min Act: -0.0000

Data Index: 699368 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7539. Min Act: -0.0000

Data Index: 609819 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1247831 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7352. Min Act: -0.0001

Data Index: 621779 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1215578 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7265. Min Act: -0.0001

Data Index: 481070 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7625. Min Act: -0.0000

Data Index: 256989 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1273729 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1044120 (C4 (Web Text))

Max Activating Token Index: 475