Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2429 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0000. Min Range: -2.0000

Max Act: 2.0000. Min Act: -0.0001

Data Index: 1152861 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.8213. Min Act: -0.0001

Data Index: 694833 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.4232. Min Act: -0.0001

Data Index: 12758 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.5004. Min Act: -0.0001

Data Index: 76830 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.2124. Min Act: -0.0001

Data Index: 38868 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.2515. Min Act: -0.0001

Data Index: 657393 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0474. Min Act: -0.0001

Data Index: 199525 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.1322. Min Act: -0.0001

Data Index: 251128 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0731. Min Act: -0.0001

Data Index: 760356 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.1277. Min Act: -0.0001

Data Index: 904811 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0917. Min Act: -0.0001

Data Index: 237578 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0419. Min Act: -0.0001

Data Index: 592555 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.1091. Min Act: -0.0001

Data Index: 487309 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.1138. Min Act: -0.0001

Data Index: 130745 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0065. Min Act: -0.0001

Data Index: 780170 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0666. Min Act: -0.0001

Data Index: 610882 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.1255. Min Act: -0.0001

Data Index: 1064321 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 2.0000. Min Range: -2.0000

Max Act: 0.9581. Min Act: -0.0001

Data Index: 1070736 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0541. Min Act: -0.0001

Data Index: 642549 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 2.0000. Min Range: -2.0000

Max Act: 1.0609. Min Act: -0.0001

Data Index: 76522 (C4 (Web Text))

Max Activating Token Index: 114