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

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

Neuron 1243 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: 0.5272. Min Range: -0.5272

Max Act: 0.5272. Min Act: -0.0002

Data Index: 46789 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.5164. Min Act: -0.0002

Data Index: 763482 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4939. Min Act: -0.0002

Data Index: 169897 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4986. Min Act: -0.0002

Data Index: 798138 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4789. Min Act: -0.0003

Data Index: 910686 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4868. Min Act: -0.0002

Data Index: 809020 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4682. Min Act: -0.0002

Data Index: 134292 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4716. Min Act: -0.0002

Data Index: 1133808 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4728. Min Act: -0.0002

Data Index: 828994 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4613. Min Act: -0.0002

Data Index: 385691 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4673. Min Act: -0.0002

Data Index: 1155451 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4569. Min Act: -0.0002

Data Index: 1043665 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4566. Min Act: -0.0002

Data Index: 175948 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4578. Min Act: -0.0002

Data Index: 205128 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4462. Min Act: -0.0002

Data Index: 1115900 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4393. Min Act: -0.0003

Data Index: 659782 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4360. Min Act: -0.0002

Data Index: 399201 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4366. Min Act: -0.0002

Data Index: 623143 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4306. Min Act: -0.0003

Data Index: 396370 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.5272. Min Range: -0.5272

Max Act: 0.4384. Min Act: -0.0002

Data Index: 61932 (C4 (Web Text))

Max Activating Token Index: 556