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

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

Neuron 3778 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5435. Min Range: -5.5435

Max Act: 5.5435. Min Act: -0.0000

Data Index: 671261 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 5.5435. Min Range: -5.5435

Max Act: 5.1300. Min Act: -0.0000

Data Index: 164504 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.6251. Min Act: -0.0000

Data Index: 455687 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.3597. Min Act: -0.0000

Data Index: 1018732 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.6850. Min Act: -0.0000

Data Index: 647767 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.6581. Min Act: -0.0000

Data Index: 243394 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.6498. Min Act: -0.0001

Data Index: 730347 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.1048. Min Act: -0.0001

Data Index: 422363 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.1101. Min Act: -0.0001

Data Index: 342072 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.2823. Min Act: -0.0001

Data Index: 492603 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.2663. Min Act: -0.0000

Data Index: 801433 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 5.5435. Min Range: -5.5435

Max Act: 4.0814. Min Act: -0.0000

Data Index: 677106 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.8504. Min Act: -0.0001

Data Index: 1189107 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.8425. Min Act: -0.0000

Data Index: 916481 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.7770. Min Act: -0.0000

Data Index: 371595 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.4512. Min Act: -0.0000

Data Index: 650285 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.5589. Min Act: -0.0000

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.5532. Min Act: -0.0001

Data Index: 1031296 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.5480. Min Act: -0.0000

Data Index: 810263 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 5.5435. Min Range: -5.5435

Max Act: 3.5516. Min Act: -0.0000

Data Index: 23407 (C4 (Web Text))

Max Activating Token Index: 255