Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2359 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.6338. Min Act: -0.0002

Data Index: 121411 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5633. Min Act: -0.0002

Data Index: 1287160 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5696. Min Act: -0.0002

Data Index: 447409 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5719. Min Act: -0.0002

Data Index: 1231707 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5722. Min Act: -0.0002

Data Index: 934806 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5552. Min Act: -0.0002

Data Index: 385728 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4671. Min Act: -0.0002

Data Index: 573255 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5151. Min Act: -0.0002

Data Index: 352715 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5653. Min Act: -0.0002

Data Index: 903943 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5156. Min Act: -0.0002

Data Index: 976016 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5362. Min Act: -0.0002

Data Index: 1212445 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4885. Min Act: -0.0002

Data Index: 1014440 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5010. Min Act: -0.0002

Data Index: 174405 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5469. Min Act: -0.0002

Data Index: 879124 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4342. Min Act: -0.0002

Data Index: 801148 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5444. Min Act: -0.0002

Data Index: 460664 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5568. Min Act: -0.0002

Data Index: 310658 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5315. Min Act: -0.0002

Data Index: 957185 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5161. Min Act: -0.0002

Data Index: 526617 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5746. Min Act: -0.0002

Data Index: 211787 (C4 (Web Text))

Max Activating Token Index: 325