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

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

Neuron 729 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: 1.0494. Min Range: -1.0494

Max Act: 1.0494. Min Act: -0.0002

Data Index: 1036432 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.0494. Min Range: -1.0494

Max Act: 1.0390. Min Act: -0.0002

Data Index: 547854 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.0494. Min Range: -1.0494

Max Act: 1.0045. Min Act: -0.0002

Data Index: 831004 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9977. Min Act: -0.0003

Data Index: 531108 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9747. Min Act: -0.0002

Data Index: 8356 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9688. Min Act: -0.0002

Data Index: 55491 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9655. Min Act: -0.0002

Data Index: 664187 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9464. Min Act: -0.0002

Data Index: 637642 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9305. Min Act: -0.0002

Data Index: 1331970 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9214. Min Act: -0.0002

Data Index: 647796 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9343. Min Act: -0.0002

Data Index: 716887 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9209. Min Act: -0.0002

Data Index: 815411 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9249. Min Act: -0.0002

Data Index: 232644 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9160. Min Act: -0.0002

Data Index: 263805 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9157. Min Act: -0.0002

Data Index: 1157736 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9393. Min Act: -0.0002

Data Index: 324837 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9191. Min Act: -0.0002

Data Index: 662071 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9196. Min Act: -0.0002

Data Index: 1351736 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9135. Min Act: -0.0002

Data Index: 406345 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.0494. Min Range: -1.0494

Max Act: 0.9136. Min Act: -0.0002

Data Index: 1218755 (C4 (Web Text))

Max Activating Token Index: 183