Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1586 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1889. Min Act: -0.0001

Data Index: 492523 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1609. Min Act: -0.0001

Data Index: 264617 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1530. Min Act: -0.0000

Data Index: 502703 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1004271 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1482. Min Act: -0.0001

Data Index: 565093 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1090352 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1609. Min Act: -0.0000

Data Index: 179697 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1206720 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1626. Min Act: -0.0000

Data Index: 341085 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1523. Min Act: -0.0001

Data Index: 978245 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1494. Min Act: -0.0001

Data Index: 55348 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1357. Min Act: -0.0000

Data Index: 113265 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1408. Min Act: -0.0001

Data Index: 81009 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1516. Min Act: -0.0001

Data Index: 434387 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1189006 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1485. Min Act: -0.0001

Data Index: 93164 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1531. Min Act: -0.0001

Data Index: 376053 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1423. Min Act: -0.0001

Data Index: 438231 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1242348 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1409. Min Act: -0.0001

Data Index: 865206 (C4 (Web Text))

Max Activating Token Index: 501