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

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

Neuron 3502 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: 3.5567. Min Range: -3.5567

Max Act: 3.1346. Min Act: -0.0000

Data Index: 773028 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 3.5567. Min Range: -3.5567

Max Act: 3.5567. Min Act: -0.0000

Data Index: 989346 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 3.5567. Min Range: -3.5567

Max Act: 3.2173. Min Act: -0.0000

Data Index: 1337809 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.9860. Min Act: -0.0000

Data Index: 322337 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.9256. Min Act: -0.0000

Data Index: 1530837 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.9218. Min Act: -0.0000

Data Index: 611487 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.6509. Min Act: -0.0000

Data Index: 804373 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.7844. Min Act: -0.0000

Data Index: 1062413 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.9324. Min Act: -0.0000

Data Index: 1613336 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.7502. Min Act: -0.0000

Data Index: 370203 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.4482. Min Act: -0.0000

Data Index: 1136961 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.7226. Min Act: -0.0000

Data Index: 569192 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.5533. Min Act: -0.0000

Data Index: 863603 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.7151. Min Act: -0.0000

Data Index: 33235 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.6967. Min Act: -0.0000

Data Index: 394804 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.6827. Min Act: -0.0000

Data Index: 1299131 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.4185. Min Act: -0.0000

Data Index: 1028693 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.2880. Min Act: -0.0000

Data Index: 355094 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 3.5567. Min Range: -3.5567

Max Act: 3.2025. Min Act: -0.0000

Data Index: 1160564 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 3.5567. Min Range: -3.5567

Max Act: 2.7432. Min Act: -0.0000

Data Index: 1640423 (Python Code)

Max Activating Token Index: 665