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

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

Neuron 4479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.5567. Min Act: -0.0000

Data Index: 1437388 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.5379. Min Act: -0.0000

Data Index: 1464595 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.5280. Min Act: -0.0000

Data Index: 1611387 (Python Code)

Max Activating Token Index: 984

Text #3

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.5104. Min Act: -0.0000

Data Index: 1466715 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.6040. Min Act: -0.0000

Data Index: 1435514 (Python Code)

Max Activating Token Index: 510

Text #5

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.3630. Min Act: -0.0000

Data Index: 1370866 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.1175. Min Act: -0.0000

Data Index: 1359957 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.3091. Min Act: -0.0000

Data Index: 1475247 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.4026. Min Act: -0.0000

Data Index: 1535475 (Python Code)

Max Activating Token Index: 974

Text #9

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.2628. Min Act: -0.0000

Data Index: 1630282 (Python Code)

Max Activating Token Index: 867

Text #10

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.2595. Min Act: -0.0000

Data Index: 1532882 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.2520. Min Act: -0.0000

Data Index: 1633529 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.3784. Min Act: -0.0000

Data Index: 1526680 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.2241. Min Act: -0.0000

Data Index: 1652376 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.2602. Min Act: -0.0000

Data Index: 1468740 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.4719. Min Act: -0.0000

Data Index: 1621733 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.3440. Min Act: -0.0000

Data Index: 1589861 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.1943. Min Act: -0.0000

Data Index: 633432 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.5711. Min Act: -0.0000

Data Index: 1631353 (Python Code)

Max Activating Token Index: 605

Text #19

Max Range: 2.6040. Min Range: -2.6040

Max Act: 2.1992. Min Act: -0.0000

Data Index: 1393839 (Python Code)

Max Activating Token Index: 513