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

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

Neuron 4624 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.8033. Min Act: -0.0001

Data Index: 300644 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6515. Min Act: -0.0001

Data Index: 1199029 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.3490. Min Act: -0.0001

Data Index: 704879 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.4671. Min Act: -0.0001

Data Index: 32044 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6643. Min Act: -0.0001

Data Index: 605011 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.3675. Min Act: -0.0001

Data Index: 322123 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.5194. Min Act: -0.0001

Data Index: 206771 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.5154. Min Act: -0.0001

Data Index: 139907 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.3228. Min Act: -0.0001

Data Index: 601720 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.3230. Min Act: -0.0001

Data Index: 208175 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.4769. Min Act: -0.0001

Data Index: 584609 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.1834. Min Act: -0.0001

Data Index: 471365 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.1937. Min Act: -0.0001

Data Index: 19697 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.0891. Min Act: -0.0001

Data Index: 1087026 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.1956. Min Act: -0.0001

Data Index: 111633 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.1759. Min Act: -0.0001

Data Index: 903540 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.4555. Min Act: -0.0001

Data Index: 492640 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.0266. Min Act: -0.0001

Data Index: 51890 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.8033. Min Range: -3.8033

Max Act: 2.9477. Min Act: -0.0001

Data Index: 887661 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.0622. Min Act: -0.0001

Data Index: 399198 (C4 (Web Text))

Max Activating Token Index: 433