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

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

Neuron 2283 in Layer 0

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: 0.1377. Min Range: -0.1377

Max Act: 0.1377. Min Act: -0.0001

Data Index: 340321 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0835. Min Act: -0.0001

Data Index: 409041 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0813. Min Act: -0.0001

Data Index: 566888 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0817. Min Act: -0.0001

Data Index: 940106 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1203996 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0748. Min Act: -0.0001

Data Index: 492461 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0719. Min Act: -0.0001

Data Index: 593442 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0730. Min Act: -0.0001

Data Index: 285908 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0740. Min Act: -0.0001

Data Index: 476697 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1000819 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0701. Min Act: -0.0001

Data Index: 664712 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1224184 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1347399 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0701. Min Act: -0.0001

Data Index: 234079 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0698. Min Act: -0.0001

Data Index: 482987 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1193555 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1283302 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0685. Min Act: -0.0001

Data Index: 135459 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0679. Min Act: -0.0001

Data Index: 530717 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0669. Min Act: -0.0001

Data Index: 711054 (C4 (Web Text))

Max Activating Token Index: 30