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

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

Neuron 3624 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: 0.1880. Min Range: -0.1880

Max Act: 0.1880. Min Act: -0.0002

Data Index: 501410 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1085. Min Act: -0.0002

Data Index: 443812 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1329948 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1012. Min Act: -0.0002

Data Index: 145428 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1004. Min Act: -0.0002

Data Index: 364694 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0942. Min Act: -0.0002

Data Index: 236984 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0938. Min Act: -0.0002

Data Index: 573690 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0938. Min Act: -0.0002

Data Index: 171567 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0945. Min Act: -0.0002

Data Index: 16756 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0905. Min Act: -0.0002

Data Index: 643869 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0885. Min Act: -0.0002

Data Index: 632597 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1218619 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0877. Min Act: -0.0002

Data Index: 883913 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0894. Min Act: -0.0002

Data Index: 346137 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0860. Min Act: -0.0002

Data Index: 693668 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1162734 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0850. Min Act: -0.0002

Data Index: 792249 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1210999 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0873. Min Act: -0.0002

Data Index: 541733 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1289666 (C4 (Web Text))

Max Activating Token Index: 627