Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 920 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0000

Data Index: 278578 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1177196 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1466800 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0479. Min Act: -0.0000

Data Index: 308595 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0451. Min Act: -0.0001

Data Index: 60972 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1425568 (Python Code)

Max Activating Token Index: 137

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0491. Min Act: -0.0000

Data Index: 545377 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1163642 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1106382 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1630958 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0421. Min Act: -0.0000

Data Index: 682210 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1618502 (Python Code)

Max Activating Token Index: 164

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1361826 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1443856 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0454. Min Act: -0.0000

Data Index: 339676 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1539755 (Python Code)

Max Activating Token Index: 668

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0388. Min Act: -0.0000

Data Index: 661191 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0425. Min Act: -0.0000

Data Index: 802143 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0380. Min Act: -0.0001

Data Index: 789687 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0404. Min Act: -0.0000

Data Index: 999923 (C4 (Web Text))

Max Activating Token Index: 288