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

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

Neuron 69 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2929. Min Act: -0.0000

Data Index: 99434 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1622409 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1649273 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1384081 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1497523 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2448. Min Act: -0.0000

Data Index: 468458 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1485705 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2500. Min Act: -0.0000

Data Index: 662897 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2442. Min Act: -0.0000

Data Index: 474010 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2453. Min Act: -0.0001

Data Index: 463342 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2238. Min Act: -0.0001

Data Index: 1390865 (Python Code)

Max Activating Token Index: 164

Text #11

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2437. Min Act: -0.0001

Data Index: 1360808 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1465515 (Python Code)

Max Activating Token Index: 596

Text #13

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2255. Min Act: -0.0000

Data Index: 968462 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2136. Min Act: -0.0001

Data Index: 510936 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1554049 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2220. Min Act: -0.0001

Data Index: 1433760 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2119. Min Act: -0.0000

Data Index: 54617 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1639237 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2082. Min Act: -0.0001

Data Index: 1399014 (Python Code)

Max Activating Token Index: 265