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

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

Neuron 3247 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1421763 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1472977 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1380332 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4402. Min Act: -0.0000

Data Index: 707654 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1519710 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1377617 (Python Code)

Max Activating Token Index: 675

Text #6

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1603220 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1555153 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4452. Min Act: -0.0000

Data Index: 664600 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1401532 (Python Code)

Max Activating Token Index: 811

Text #10

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1425177 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1370670 (Python Code)

Max Activating Token Index: 870

Text #12

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4184. Min Act: -0.0000

Data Index: 505667 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1567638 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1634825 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1392169 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1386534 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4190. Min Act: -0.0000

Data Index: 752157 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1374610 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1362616 (Python Code)

Max Activating Token Index: 216