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

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

Neuron 20 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: 1.5762. Min Range: -1.5762

Max Act: 1.5762. Min Act: -0.0002

Data Index: 1052238 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.5253. Min Act: -0.0002

Data Index: 356947 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4187. Min Act: -0.0002

Data Index: 639573 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.3818. Min Act: -0.0002

Data Index: 705120 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.3767. Min Act: -0.0002

Data Index: 1011215 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.3799. Min Act: -0.0002

Data Index: 845012 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.3132. Min Act: -0.0002

Data Index: 449208 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.3237. Min Act: -0.0002

Data Index: 9543 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2647. Min Act: -0.0002

Data Index: 575061 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2696. Min Act: -0.0002

Data Index: 247292 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.3178. Min Act: -0.0002

Data Index: 418475 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2478. Min Act: -0.0002

Data Index: 73562 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2245. Min Act: -0.0002

Data Index: 1219529 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2650. Min Act: -0.0002

Data Index: 377006 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2495. Min Act: -0.0002

Data Index: 1270675 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2872. Min Act: -0.0002

Data Index: 675026 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2188. Min Act: -0.0002

Data Index: 330150 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1963. Min Act: -0.0002

Data Index: 1002010 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1877. Min Act: -0.0002

Data Index: 848095 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1884. Min Act: -0.0002

Data Index: 796923 (C4 (Web Text))

Max Activating Token Index: 403