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

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

Neuron 2585 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: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0001

Data Index: 1432818 (Python Code)

Max Activating Token Index: 500

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0002

Data Index: 940387 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1444709 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0002

Data Index: 386326 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1182032 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0058. Min Act: -0.0002

Data Index: 90226 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0058. Min Act: -0.0002

Data Index: 180721 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0057. Min Act: -0.0002

Data Index: 499851 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0057. Min Act: -0.0002

Data Index: 508430 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1417271 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0056. Min Act: -0.0002

Data Index: 278187 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1420318 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0055. Min Act: -0.0002

Data Index: 294093 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1362214 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1425931 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1576441 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1642125 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1510068 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0002

Data Index: 50624 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1293600 (C4 (Web Text))

Max Activating Token Index: 14