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

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

Neuron 675 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.6333. Min Act: -0.0000

Data Index: 872973 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5988. Min Act: -0.0000

Data Index: 838746 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5981. Min Act: -0.0000

Data Index: 71048 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5559. Min Act: -0.0000

Data Index: 906932 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5320. Min Act: -0.0000

Data Index: 106874 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5050. Min Act: -0.0000

Data Index: 766496 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4762. Min Act: -0.0000

Data Index: 961499 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5337. Min Act: -0.0000

Data Index: 862171 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1288967 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5172. Min Act: -0.0000

Data Index: 584983 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1187732 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1292025 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4665. Min Act: -0.0000

Data Index: 410917 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4701. Min Act: -0.0000

Data Index: 386866 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4915. Min Act: -0.0000

Data Index: 304303 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4912. Min Act: -0.0000

Data Index: 648308 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4749. Min Act: -0.0000

Data Index: 940929 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4498. Min Act: -0.0000

Data Index: 453026 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4341. Min Act: -0.0000

Data Index: 231130 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4197. Min Act: -0.0000

Data Index: 964276 (C4 (Web Text))

Max Activating Token Index: 634