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

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

Neuron 4972 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8915. Min Act: -0.0002

Data Index: 1504228 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8742. Min Act: -0.0002

Data Index: 1652403 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8325. Min Act: -0.0002

Data Index: 1562993 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8528. Min Act: -0.0002

Data Index: 1386316 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8444. Min Act: -0.0002

Data Index: 1580781 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1380237 (Python Code)

Max Activating Token Index: 106

Text #6

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8278. Min Act: -0.0002

Data Index: 1607530 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8203. Min Act: -0.0002

Data Index: 1578259 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7988. Min Act: -0.0002

Data Index: 1515134 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8010. Min Act: -0.0002

Data Index: 1410200 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8126. Min Act: -0.0002

Data Index: 1407717 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8073. Min Act: -0.0002

Data Index: 1605377 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8036. Min Act: -0.0002

Data Index: 1399494 (Python Code)

Max Activating Token Index: 257

Text #13

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7834. Min Act: -0.0002

Data Index: 1501431 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7898. Min Act: -0.0002

Data Index: 1629933 (Python Code)

Max Activating Token Index: 505

Text #15

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7864. Min Act: -0.0002

Data Index: 1387186 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7925. Min Act: -0.0002

Data Index: 1492259 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7898. Min Act: -0.0002

Data Index: 1599409 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7929. Min Act: -0.0002

Data Index: 1369689 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7892. Min Act: -0.0002

Data Index: 1463421 (Python Code)

Max Activating Token Index: 8