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

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

Neuron 1072 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.4894. Min Act: -0.0000

Data Index: 148377 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.3609. Min Act: -0.0000

Data Index: 380118 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.3735. Min Act: -0.0000

Data Index: 243443 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9030. Min Act: -0.0000

Data Index: 903241 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.5362. Min Act: -0.0000

Data Index: 464831 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.5909. Min Act: -0.0000

Data Index: 944515 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.5611. Min Act: -0.0000

Data Index: 335690 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.5343. Min Act: -0.0000

Data Index: 169982 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.5176. Min Act: -0.0000

Data Index: 492531 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4195. Min Act: -0.0000

Data Index: 659185 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4883. Min Act: -0.0000

Data Index: 899633 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1002269 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4698. Min Act: -0.0000

Data Index: 841033 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4471. Min Act: -0.0000

Data Index: 928053 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4614. Min Act: -0.0000

Data Index: 908378 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4601. Min Act: -0.0000

Data Index: 756940 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4434. Min Act: -0.0000

Data Index: 933865 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4513. Min Act: -0.0000

Data Index: 959640 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1008240 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1324552 (C4 (Web Text))

Max Activating Token Index: 570