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

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

Neuron 1247 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1393. Min Act: -0.0000

Data Index: 400032 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1255. Min Act: -0.0000

Data Index: 412495 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1080752 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1062. Min Act: -0.0000

Data Index: 445827 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1108128 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1271492 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1022. Min Act: -0.0000

Data Index: 376601 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0985. Min Act: -0.0000

Data Index: 391947 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1016699 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0961. Min Act: -0.0000

Data Index: 769143 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1010. Min Act: -0.0000

Data Index: 165378 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1332785 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0924. Min Act: -0.0000

Data Index: 879421 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1047935 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1031638 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1216680 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0933. Min Act: -0.0000

Data Index: 654757 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1332683 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0890. Min Act: -0.0000

Data Index: 925219 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0890. Min Act: -0.0000

Data Index: 831496 (C4 (Web Text))

Max Activating Token Index: 353