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

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

Neuron 1440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2730. Min Range: -2.2730

Max Act: 2.2730. Min Act: -0.0000

Data Index: 1538421 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 2.2730. Min Range: -2.2730

Max Act: 2.1958. Min Act: -0.0000

Data Index: 1489332 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.9367. Min Act: -0.0000

Data Index: 1493534 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 2.2730. Min Range: -2.2730

Max Act: 2.0491. Min Act: -0.0000

Data Index: 1366221 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 2.2730. Min Range: -2.2730

Max Act: 2.1789. Min Act: -0.0000

Data Index: 1533524 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.8580. Min Act: -0.0000

Data Index: 1401534 (Python Code)

Max Activating Token Index: 358

Text #6

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.9764. Min Act: -0.0000

Data Index: 1432436 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.8905. Min Act: 0.0000

Data Index: 1394607 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.7443. Min Act: -0.0000

Data Index: 1540563 (Python Code)

Max Activating Token Index: 602

Text #9

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.9628. Min Act: -0.0000

Data Index: 1494981 (Python Code)

Max Activating Token Index: 205

Text #10

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1458578 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.7634. Min Act: -0.0000

Data Index: 1550395 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.7993. Min Act: -0.0000

Data Index: 1489699 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1508259 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.5589. Min Act: -0.0000

Data Index: 1513970 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.8099. Min Act: 0.0000

Data Index: 1423610 (Python Code)

Max Activating Token Index: 741

Text #16

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1609511 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.6673. Min Act: -0.0000

Data Index: 1557301 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1614634 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 2.2730. Min Range: -2.2730

Max Act: 1.4605. Min Act: -0.0000

Data Index: 1580527 (Python Code)

Max Activating Token Index: 892