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

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

Neuron 2152 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6445. Min Range: -3.6445

Max Act: 3.6445. Min Act: -0.0000

Data Index: 1492666 (Python Code)

Max Activating Token Index: 982

Text #1

Max Range: 3.6445. Min Range: -3.6445

Max Act: 2.5928. Min Act: -0.0000

Data Index: 1656795 (Python Code)

Max Activating Token Index: 514

Text #2

Max Range: 3.6445. Min Range: -3.6445

Max Act: 2.6103. Min Act: -0.0000

Data Index: 1588244 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 3.6445. Min Range: -3.6445

Max Act: 2.4803. Min Act: -0.0000

Data Index: 1536585 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 3.6445. Min Range: -3.6445

Max Act: 2.2392. Min Act: -0.0000

Data Index: 1585227 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 3.6445. Min Range: -3.6445

Max Act: 2.0916. Min Act: -0.0000

Data Index: 1467587 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.9914. Min Act: -0.0000

Data Index: 1604993 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1562654 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 3.6445. Min Range: -3.6445

Max Act: 2.2232. Min Act: -0.0000

Data Index: 1525281 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.6574. Min Act: -0.0000

Data Index: 228926 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1443731 (Python Code)

Max Activating Token Index: 781

Text #11

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.9674. Min Act: -0.0000

Data Index: 1503208 (Python Code)

Max Activating Token Index: 634

Text #12

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1509881 (Python Code)

Max Activating Token Index: 1010

Text #13

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.6771. Min Act: -0.0000

Data Index: 1439242 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1491486 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.5347. Min Act: -0.0000

Data Index: 483060 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1362971 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.4430. Min Act: 0.0000

Data Index: 1210423 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1573884 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 3.6445. Min Range: -3.6445

Max Act: 1.5499. Min Act: -0.0000

Data Index: 920868 (C4 (Web Text))

Max Activating Token Index: 679