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

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

Neuron 663 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.9918. Min Act: -0.0000

Data Index: 1133810 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.4023. Min Act: -0.0001

Data Index: 164899 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.7413. Min Act: -0.0000

Data Index: 228593 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.1286. Min Act: -0.0001

Data Index: 29295 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.2152. Min Act: -0.0001

Data Index: 1044656 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.3955. Min Act: -0.0001

Data Index: 899343 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.2980. Min Act: -0.0001

Data Index: 859812 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9344. Min Act: -0.0001

Data Index: 26753 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.2592. Min Act: -0.0001

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9666. Min Act: -0.0001

Data Index: 1207636 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.2879. Min Act: -0.0001

Data Index: 608634 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.0679. Min Act: -0.0000

Data Index: 1081523 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9532. Min Act: -0.0000

Data Index: 1183755 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9936. Min Act: -0.0001

Data Index: 92876 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9874. Min Act: -0.0000

Data Index: 597979 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9941. Min Act: -0.0001

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.3026. Min Act: -0.0000

Data Index: 944501 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.6472. Min Act: -0.0000

Data Index: 720724 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.0344. Min Act: -0.0000

Data Index: 884392 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.1323. Min Act: -0.0001

Data Index: 276604 (C4 (Web Text))

Max Activating Token Index: 416