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

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

Neuron 385 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: 2.2170. Min Range: -2.2170

Max Act: 2.2170. Min Act: -0.0002

Data Index: 952598 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 2.2170. Min Range: -2.2170

Max Act: 2.1142. Min Act: -0.0002

Data Index: 899539 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 2.2170. Min Range: -2.2170

Max Act: 2.0338. Min Act: -0.0002

Data Index: 33413 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 2.2170. Min Range: -2.2170

Max Act: 2.0633. Min Act: -0.0002

Data Index: 836863 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 2.2170. Min Range: -2.2170

Max Act: 2.0572. Min Act: -0.0002

Data Index: 24430 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9874. Min Act: -0.0002

Data Index: 333786 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9425. Min Act: -0.0002

Data Index: 1117636 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9395. Min Act: -0.0002

Data Index: 926164 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9658. Min Act: -0.0002

Data Index: 554678 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9808. Min Act: -0.0002

Data Index: 152069 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9308. Min Act: -0.0002

Data Index: 802043 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9492. Min Act: -0.0002

Data Index: 274710 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9082. Min Act: -0.0002

Data Index: 943850 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.8989. Min Act: -0.0002

Data Index: 1117724 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9542. Min Act: -0.0002

Data Index: 782717 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9287. Min Act: -0.0002

Data Index: 897661 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9080. Min Act: -0.0002

Data Index: 1308849 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9560. Min Act: -0.0002

Data Index: 450675 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9394. Min Act: -0.0003

Data Index: 1289489 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 2.2170. Min Range: -2.2170

Max Act: 1.9361. Min Act: -0.0002

Data Index: 862462 (C4 (Web Text))

Max Activating Token Index: 320