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

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

Neuron 647 in Layer 0

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: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 66488 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1047470 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 261967 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 976747 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 287399 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0002

Data Index: 184545 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 894322 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 982887 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 628394 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0804. Min Act: -0.0001

Data Index: 961520 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0757. Min Act: -0.0001

Data Index: 483139 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0753. Min Act: -0.0002

Data Index: 278354 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0763. Min Act: -0.0001

Data Index: 470646 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0742. Min Act: -0.0001

Data Index: 440553 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0741. Min Act: -0.0001

Data Index: 4363 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1053889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1301338 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0706. Min Act: -0.0001

Data Index: 432067 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0691. Min Act: -0.0001

Data Index: 447251 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0691. Min Act: -0.0001

Data Index: 806912 (C4 (Web Text))

Max Activating Token Index: 3