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

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

Neuron 3724 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: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0002

Data Index: 870802 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0858. Min Act: -0.0002

Data Index: 15465 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1174838 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1301759 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1219754 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0821. Min Act: -0.0002

Data Index: 55750 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1090540 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0793. Min Act: -0.0002

Data Index: 171734 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0772. Min Act: -0.0002

Data Index: 349610 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0785. Min Act: -0.0002

Data Index: 470436 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0761. Min Act: -0.0002

Data Index: 726042 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0779. Min Act: -0.0002

Data Index: 510338 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0747. Min Act: -0.0002

Data Index: 414639 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0755. Min Act: -0.0002

Data Index: 911209 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0716. Min Act: -0.0002

Data Index: 899696 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1133841 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1171949 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1274538 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1061817 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0654. Min Act: -0.0002

Data Index: 38512 (C4 (Web Text))

Max Activating Token Index: 251