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

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

Neuron 5330 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5750. Min Range: -2.5750

Max Act: 2.5750. Min Act: -0.0000

Data Index: 151539 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 2.5750. Min Range: -2.5750

Max Act: 2.1769. Min Act: -0.0000

Data Index: 270585 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 2.5750. Min Range: -2.5750

Max Act: 2.1572. Min Act: -0.0000

Data Index: 702177 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1072931 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 2.5750. Min Range: -2.5750

Max Act: 2.0308. Min Act: -0.0000

Data Index: 288704 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.8097. Min Act: -0.0000

Data Index: 142735 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.8659. Min Act: -0.0000

Data Index: 412370 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.8418. Min Act: -0.0000

Data Index: 495907 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.8012. Min Act: -0.0000

Data Index: 1173123 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1286498 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.7647. Min Act: -0.0000

Data Index: 742481 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.7413. Min Act: -0.0000

Data Index: 813095 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.6748. Min Act: -0.0000

Data Index: 1340144 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.6602. Min Act: -0.0000

Data Index: 285279 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1039533 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.5210. Min Act: -0.0000

Data Index: 630782 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.5911. Min Act: -0.0000

Data Index: 564960 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.5171. Min Act: -0.0000

Data Index: 435731 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.5989. Min Act: -0.0000

Data Index: 704434 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 2.5750. Min Range: -2.5750

Max Act: 1.5737. Min Act: -0.0000

Data Index: 799171 (C4 (Web Text))

Max Activating Token Index: 332