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

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

Neuron 3664 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5785. Min Act: -0.0001

Data Index: 182416 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4775. Min Act: -0.0001

Data Index: 724430 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5116. Min Act: -0.0001

Data Index: 1444120 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5317. Min Act: -0.0001

Data Index: 1654296 (Python Code)

Max Activating Token Index: 223

Text #4

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5367. Min Act: -0.0001

Data Index: 680292 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4986. Min Act: -0.0001

Data Index: 1256135 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4809. Min Act: -0.0001

Data Index: 567934 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4763. Min Act: -0.0001

Data Index: 1454752 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4932. Min Act: -0.0001

Data Index: 864333 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4733. Min Act: -0.0000

Data Index: 455684 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4858. Min Act: -0.0001

Data Index: 1579497 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4540. Min Act: -0.0000

Data Index: 198701 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4545. Min Act: -0.0000

Data Index: 729620 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4523. Min Act: -0.0000

Data Index: 699696 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4746. Min Act: -0.0001

Data Index: 720060 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4394. Min Act: -0.0001

Data Index: 815431 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4550. Min Act: -0.0001

Data Index: 341363 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1429094 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4400. Min Act: -0.0001

Data Index: 361428 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4523. Min Act: -0.0001

Data Index: 1537119 (Python Code)

Max Activating Token Index: 975