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

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

Neuron 6003 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.4900. Min Act: -0.0000

Data Index: 720943 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.4422. Min Act: -0.0000

Data Index: 726281 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2811. Min Act: -0.0000

Data Index: 1640985 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3539. Min Act: -0.0000

Data Index: 1451342 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.1558. Min Act: -0.0000

Data Index: 163340 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.1364. Min Act: -0.0000

Data Index: 548451 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.1112. Min Act: -0.0000

Data Index: 1229226 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.1011. Min Act: -0.0000

Data Index: 301558 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.0594. Min Act: -0.0000

Data Index: 1425404 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.0429. Min Act: -0.0000

Data Index: 1198073 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.8733. Min Act: -0.0000

Data Index: 1536643 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.9594. Min Act: -0.0000

Data Index: 703954 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.9686. Min Act: -0.0000

Data Index: 91881 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.9328. Min Act: -0.0000

Data Index: 1020474 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.9289. Min Act: -0.0000

Data Index: 714987 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.0338. Min Act: -0.0000

Data Index: 195206 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.8937. Min Act: -0.0000

Data Index: 765583 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.8475. Min Act: -0.0000

Data Index: 449429 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.8332. Min Act: -0.0000

Data Index: 993475 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 3.4900. Min Range: -3.4900

Max Act: 2.9752. Min Act: -0.0000

Data Index: 949087 (C4 (Web Text))

Max Activating Token Index: 510