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

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

Neuron 5885 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: 1.9778. Min Range: -1.9778

Max Act: 1.9778. Min Act: -0.0002

Data Index: 499331 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.7794. Min Act: -0.0003

Data Index: 988916 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.7193. Min Act: -0.0003

Data Index: 1122210 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.6615. Min Act: -0.0002

Data Index: 122492 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.6504. Min Act: -0.0002

Data Index: 361617 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.6671. Min Act: -0.0002

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.6567. Min Act: -0.0002

Data Index: 450046 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5924. Min Act: -0.0003

Data Index: 368747 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5992. Min Act: -0.0003

Data Index: 291313 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5376. Min Act: -0.0002

Data Index: 536890 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5205. Min Act: -0.0003

Data Index: 624652 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5305. Min Act: -0.0003

Data Index: 878225 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5107. Min Act: -0.0002

Data Index: 1078117 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5240. Min Act: -0.0002

Data Index: 877570 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5516. Min Act: -0.0002

Data Index: 781157 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5144. Min Act: -0.0002

Data Index: 758194 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5256. Min Act: -0.0003

Data Index: 391628 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5105. Min Act: -0.0003

Data Index: 709657 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5264. Min Act: -0.0003

Data Index: 683738 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.9778. Min Range: -1.9778

Max Act: 1.5047. Min Act: -0.0003

Data Index: 900318 (C4 (Web Text))

Max Activating Token Index: 41