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

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

Neuron 636 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9564. Min Range: -6.9564

Max Act: 6.9564. Min Act: -0.0000

Data Index: 1445877 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 6.9564. Min Range: -6.9564

Max Act: 6.4877. Min Act: -0.0000

Data Index: 1396000 (Python Code)

Max Activating Token Index: 399

Text #2

Max Range: 6.9564. Min Range: -6.9564

Max Act: 6.4417. Min Act: -0.0000

Data Index: 1489912 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 6.9564. Min Range: -6.9564

Max Act: 6.2721. Min Act: -0.0000

Data Index: 1426405 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 6.9564. Min Range: -6.9564

Max Act: 6.5130. Min Act: -0.0000

Data Index: 1646205 (Python Code)

Max Activating Token Index: 82

Text #5

Max Range: 6.9564. Min Range: -6.9564

Max Act: 6.2932. Min Act: -0.0000

Data Index: 1387830 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 6.9564. Min Range: -6.9564

Max Act: 6.0946. Min Act: -0.0000

Data Index: 1442863 (Python Code)

Max Activating Token Index: 500

Text #7

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.9987. Min Act: -0.0000

Data Index: 1528740 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.8070. Min Act: -0.0000

Data Index: 1511952 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.9276. Min Act: -0.0000

Data Index: 1565682 (Python Code)

Max Activating Token Index: 422

Text #10

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.7353. Min Act: -0.0000

Data Index: 1469488 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.4725. Min Act: -0.0000

Data Index: 1372270 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.4792. Min Act: -0.0000

Data Index: 1494822 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.2544. Min Act: -0.0000

Data Index: 1522286 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.3711. Min Act: -0.0000

Data Index: 1588495 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.1725. Min Act: -0.0000

Data Index: 1445236 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.3389. Min Act: -0.0000

Data Index: 1482083 (Python Code)

Max Activating Token Index: 469

Text #17

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.0033. Min Act: -0.0000

Data Index: 1380241 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 6.9564. Min Range: -6.9564

Max Act: 4.8179. Min Act: -0.0000

Data Index: 1636119 (Python Code)

Max Activating Token Index: 332

Text #19

Max Range: 6.9564. Min Range: -6.9564

Max Act: 5.2642. Min Act: -0.0000

Data Index: 1537900 (Python Code)

Max Activating Token Index: 214