Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1945 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.8313. Min Act: -0.0001

Data Index: 591591 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.6964. Min Act: -0.0000

Data Index: 186354 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1268362 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5425. Min Act: -0.0001

Data Index: 957115 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5092. Min Act: -0.0000

Data Index: 460371 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5077. Min Act: -0.0001

Data Index: 532561 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5040. Min Act: -0.0000

Data Index: 117120 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1104596 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4827. Min Act: -0.0000

Data Index: 312948 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4555. Min Act: -0.0001

Data Index: 1277742 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1128529 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4536. Min Act: -0.0000

Data Index: 870903 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4514. Min Act: -0.0001

Data Index: 283575 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4470. Min Act: -0.0001

Data Index: 1123630 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1266009 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4391. Min Act: -0.0000

Data Index: 217225 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1064614 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4292. Min Act: -0.0000

Data Index: 318265 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4286. Min Act: -0.0000

Data Index: 439302 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.8313. Min Range: -0.8313

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1236136 (C4 (Web Text))

Max Activating Token Index: 898