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

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

Neuron 2748 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: 1.0889. Min Range: -1.0889

Max Act: 0.9959. Min Act: -0.0001

Data Index: 1521109 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 1.0889. Min Range: -1.0889

Max Act: 1.0889. Min Act: -0.0001

Data Index: 1649633 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.9863. Min Act: -0.0001

Data Index: 1524858 (Python Code)

Max Activating Token Index: 78

Text #3

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.9406. Min Act: -0.0000

Data Index: 990486 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1497330 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.7985. Min Act: -0.0001

Data Index: 1596039 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.8017. Min Act: -0.0001

Data Index: 1596009 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1555437 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1624956 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1580182 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1584909 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.7131. Min Act: -0.0000

Data Index: 660052 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6838. Min Act: -0.0001

Data Index: 1648693 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6434. Min Act: -0.0001

Data Index: 699906 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6358. Min Act: -0.0001

Data Index: 1628081 (Python Code)

Max Activating Token Index: 259

Text #15

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6457. Min Act: 0.0000

Data Index: 1478572 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6473. Min Act: -0.0001

Data Index: 1491406 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1533166 (Python Code)

Max Activating Token Index: 255

Text #18

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1409293 (Python Code)

Max Activating Token Index: 989

Text #19

Max Range: 1.0889. Min Range: -1.0889

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1076358 (C4 (Web Text))

Max Activating Token Index: 204