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

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

Neuron 5185 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: 2.9103. Min Range: -2.9103

Max Act: 2.9103. Min Act: -0.0002

Data Index: 1092898 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.9103. Min Act: -0.0002

Data Index: 1231776 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.6180. Min Act: -0.0002

Data Index: 265038 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.5669. Min Act: -0.0002

Data Index: 701260 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.5389. Min Act: -0.0002

Data Index: 188629 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.5389. Min Act: -0.0002

Data Index: 942089 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.3166. Min Act: -0.0002

Data Index: 823082 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.2870. Min Act: -0.0002

Data Index: 1275091 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.2646. Min Act: -0.0002

Data Index: 1242560 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.1770. Min Act: -0.0002

Data Index: 422199 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.1592. Min Act: -0.0002

Data Index: 272104 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.1917. Min Act: -0.0002

Data Index: 797494 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.0897. Min Act: -0.0002

Data Index: 523415 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.1108. Min Act: -0.0002

Data Index: 891656 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.0546. Min Act: -0.0003

Data Index: 774061 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.0205. Min Act: -0.0002

Data Index: 1231091 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.0984. Min Act: -0.0002

Data Index: 38566 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.0464. Min Act: -0.0002

Data Index: 635710 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.0504. Min Act: -0.0002

Data Index: 265814 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 2.9103. Min Range: -2.9103

Max Act: 2.0150. Min Act: -0.0002

Data Index: 324529 (C4 (Web Text))

Max Activating Token Index: 10