Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1393. Min Act: -0.0001

Data Index: 160454 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1001. Min Act: -0.0001

Data Index: 49011 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1159741 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1063. Min Act: -0.0001

Data Index: 531306 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1297295 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0908. Min Act: -0.0001

Data Index: 271298 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0925. Min Act: -0.0001

Data Index: 887397 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0879. Min Act: -0.0001

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0940. Min Act: -0.0001

Data Index: 795334 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0909. Min Act: -0.0001

Data Index: 685299 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0940. Min Act: -0.0001

Data Index: 206569 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0938. Min Act: -0.0001

Data Index: 703090 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1188336 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0863. Min Act: -0.0001

Data Index: 677968 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0901. Min Act: -0.0001

Data Index: 492567 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0959. Min Act: -0.0001

Data Index: 942775 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0910. Min Act: -0.0001

Data Index: 767352 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1223348 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0901. Min Act: -0.0001

Data Index: 456901 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1041084 (C4 (Web Text))

Max Activating Token Index: 921