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

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

Neuron 1741 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: 1.9697. Min Range: -1.9697

Max Act: 1.9697. Min Act: -0.0002

Data Index: 451600 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.9203. Min Act: -0.0002

Data Index: 44197 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.8637. Min Act: -0.0002

Data Index: 701029 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.7394. Min Act: -0.0002

Data Index: 871008 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.7350. Min Act: -0.0002

Data Index: 169716 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6843. Min Act: -0.0002

Data Index: 755548 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.7105. Min Act: -0.0002

Data Index: 720658 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6758. Min Act: -0.0002

Data Index: 326744 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.7376. Min Act: -0.0002

Data Index: 1328292 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6369. Min Act: -0.0002

Data Index: 1298783 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6498. Min Act: -0.0002

Data Index: 282532 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6507. Min Act: -0.0002

Data Index: 1107844 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6940. Min Act: -0.0002

Data Index: 1049824 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6211. Min Act: -0.0002

Data Index: 398913 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6639. Min Act: -0.0002

Data Index: 630711 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6265. Min Act: -0.0003

Data Index: 565055 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6288. Min Act: -0.0002

Data Index: 1300219 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6382. Min Act: -0.0002

Data Index: 940848 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6194. Min Act: -0.0003

Data Index: 744614 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.9697. Min Range: -1.9697

Max Act: 1.6170. Min Act: -0.0002

Data Index: 77684 (C4 (Web Text))

Max Activating Token Index: 26