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

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

Neuron 2972 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.5854. Min Act: -0.0000

Data Index: 438426 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1506512 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4355. Min Act: -0.0000

Data Index: 329266 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1620499 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3966. Min Act: -0.0000

Data Index: 677944 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1603928 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4277. Min Act: -0.0000

Data Index: 109529 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1457610 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1482067 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1395047 (Python Code)

Max Activating Token Index: 546

Text #10

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1362957 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1405685 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1548095 (Python Code)

Max Activating Token Index: 764

Text #13

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1515754 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3559. Min Act: -0.0000

Data Index: 384161 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1531183 (Python Code)

Max Activating Token Index: 832

Text #16

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1587381 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1077615 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1549678 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1458935 (Python Code)

Max Activating Token Index: 998