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

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

Neuron 4167 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.4453. Min Act: -0.0001

Data Index: 1503172 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2615. Min Act: -0.0001

Data Index: 1648193 (Python Code)

Max Activating Token Index: 782

Text #2

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.4346. Min Act: -0.0001

Data Index: 1407630 (Python Code)

Max Activating Token Index: 700

Text #3

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2486. Min Act: -0.0001

Data Index: 1380087 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.4375. Min Act: -0.0001

Data Index: 1614016 (Python Code)

Max Activating Token Index: 631

Text #5

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.4176. Min Act: -0.0001

Data Index: 1483925 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.4212. Min Act: -0.0001

Data Index: 1428029 (Python Code)

Max Activating Token Index: 578

Text #7

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.4187. Min Act: -0.0001

Data Index: 1377968 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2327. Min Act: -0.0001

Data Index: 1441553 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.5834. Min Act: -0.0001

Data Index: 1431161 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2206. Min Act: -0.0001

Data Index: 1421761 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.3952. Min Act: -0.0001

Data Index: 1575436 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.1970. Min Act: -0.0001

Data Index: 1647115 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2842. Min Act: -0.0001

Data Index: 1432326 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2631. Min Act: -0.0001

Data Index: 1395072 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2728. Min Act: -0.0001

Data Index: 1593314 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.0937. Min Act: -0.0001

Data Index: 1450687 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2695. Min Act: -0.0001

Data Index: 1533116 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2629. Min Act: -0.0001

Data Index: 1390265 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 5.5834. Min Range: -5.5834

Max Act: 5.2495. Min Act: -0.0001

Data Index: 1612911 (Python Code)

Max Activating Token Index: 59