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

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

Neuron 4388 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: 0.1278. Min Range: -0.1278

Max Act: 0.1278. Min Act: -0.0002

Data Index: 245013 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1106. Min Act: -0.0002

Data Index: 450669 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1074. Min Act: -0.0002

Data Index: 634735 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1063. Min Act: -0.0002

Data Index: 407542 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1195461 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1016. Min Act: -0.0002

Data Index: 466129 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1036. Min Act: -0.0002

Data Index: 430967 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1026. Min Act: -0.0002

Data Index: 52044 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1000. Min Act: -0.0002

Data Index: 2575 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1342513 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1011. Min Act: -0.0002

Data Index: 509538 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1039. Min Act: -0.0002

Data Index: 423060 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1010. Min Act: -0.0002

Data Index: 161942 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1028485 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0966. Min Act: -0.0002

Data Index: 887074 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0961. Min Act: -0.0002

Data Index: 791204 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0967. Min Act: -0.0002

Data Index: 771360 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0970. Min Act: -0.0002

Data Index: 36429 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1106889 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0955. Min Act: -0.0002

Data Index: 640529 (C4 (Web Text))

Max Activating Token Index: 64