Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5033 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.8011. Min Act: -0.0000

Data Index: 732598 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.4068. Min Act: -0.0000

Data Index: 710325 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3744. Min Act: -0.0000

Data Index: 597698 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3552. Min Act: -0.0000

Data Index: 929983 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1311361 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1411442 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3237. Min Act: -0.0000

Data Index: 489311 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1500828 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1632753 (Python Code)

Max Activating Token Index: 1015

Text #9

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1167781 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1493152 (Python Code)

Max Activating Token Index: 592

Text #11

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1022151 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3253. Min Act: -0.0000

Data Index: 490608 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1610075 (Python Code)

Max Activating Token Index: 248

Text #14

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1545991 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.2978. Min Act: -0.0000

Data Index: 328470 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.4149. Min Act: -0.0000

Data Index: 13996 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1564335 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1120068 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1569902 (Python Code)

Max Activating Token Index: 714