Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4835 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5878. Min Act: -0.0000

Data Index: 370493 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4785. Min Act: -0.0000

Data Index: 309954 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5061. Min Act: 0.0001

Data Index: 947729 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4479. Min Act: -0.0000

Data Index: 121972 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4333. Min Act: -0.0000

Data Index: 657971 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4255. Min Act: -0.0000

Data Index: 435979 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1270512 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4462. Min Act: -0.0000

Data Index: 868168 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4197. Min Act: -0.0000

Data Index: 564736 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3644. Min Act: -0.0000

Data Index: 737714 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3948. Min Act: 0.0000

Data Index: 610125 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4045. Min Act: -0.0000

Data Index: 571414 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3834. Min Act: -0.0000

Data Index: 963094 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1012095 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1243352 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3694. Min Act: -0.0000

Data Index: 296127 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1293926 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3781. Min Act: -0.0000

Data Index: 304834 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3647. Min Act: 0.0001

Data Index: 867051 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.3610. Min Act: -0.0000

Data Index: 67367 (C4 (Web Text))

Max Activating Token Index: 543