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

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

Neuron 5908 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: 3.2597. Min Range: -3.2597

Max Act: 3.1486. Min Act: -0.0000

Data Index: 277082 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.2597. Min Range: -3.2597

Max Act: 3.2597. Min Act: -0.0000

Data Index: 330113 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.7624. Min Act: -0.0001

Data Index: 42633 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.7066. Min Act: -0.0001

Data Index: 354225 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.6745. Min Act: -0.0001

Data Index: 780735 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.6581. Min Act: -0.0000

Data Index: 143671 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.5918. Min Act: -0.0000

Data Index: 992113 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.7134. Min Act: -0.0000

Data Index: 229214 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.3736. Min Act: -0.0000

Data Index: 1239961 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.3542. Min Act: -0.0001

Data Index: 290576 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.5389. Min Act: -0.0000

Data Index: 1036491 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.3261. Min Act: -0.0001

Data Index: 1353600 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.2895. Min Act: -0.0000

Data Index: 572188 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.1967. Min Act: -0.0000

Data Index: 169273 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.4880. Min Act: -0.0001

Data Index: 495124 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.3565. Min Act: -0.0000

Data Index: 1303481 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.2246. Min Act: -0.0001

Data Index: 1215346 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.2329. Min Act: -0.0001

Data Index: 431490 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.1902. Min Act: -0.0000

Data Index: 886149 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.2597. Min Range: -3.2597

Max Act: 2.1785. Min Act: -0.0000

Data Index: 178573 (C4 (Web Text))

Max Activating Token Index: 202