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

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

Neuron 973 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1238124 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1147257 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5444. Min Act: -0.0000

Data Index: 678950 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5210. Min Act: -0.0000

Data Index: 392108 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4995. Min Act: -0.0000

Data Index: 392974 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4503. Min Act: -0.0000

Data Index: 479674 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1121542 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4559. Min Act: -0.0000

Data Index: 968464 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4527. Min Act: -0.0000

Data Index: 951615 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4517. Min Act: -0.0000

Data Index: 495742 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.3987. Min Act: -0.0000

Data Index: 98953 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1117458 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1417396 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1427924 (Python Code)

Max Activating Token Index: 811

Text #14

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4564. Min Act: -0.0000

Data Index: 611110 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4106. Min Act: -0.0000

Data Index: 389538 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4180. Min Act: -0.0000

Data Index: 60763 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4322. Min Act: -0.0000

Data Index: 314320 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1134156 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4293. Min Act: -0.0000

Data Index: 626654 (C4 (Web Text))

Max Activating Token Index: 784