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

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

Neuron 432 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2358. Min Range: -2.2358

Max Act: 2.2358. Min Act: -0.0001

Data Index: 1035231 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.9055. Min Act: -0.0001

Data Index: 557506 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 2.2358. Min Range: -2.2358

Max Act: 2.0966. Min Act: -0.0001

Data Index: 990566 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 2.2358. Min Range: -2.2358

Max Act: 2.0088. Min Act: -0.0001

Data Index: 448965 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8851. Min Act: -0.0001

Data Index: 775775 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.9965. Min Act: -0.0001

Data Index: 488548 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8763. Min Act: -0.0001

Data Index: 781243 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8899. Min Act: -0.0001

Data Index: 497075 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.7839. Min Act: -0.0000

Data Index: 681105 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8525. Min Act: -0.0000

Data Index: 249496 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.9525. Min Act: -0.0001

Data Index: 1150229 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8141. Min Act: -0.0001

Data Index: 374510 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8091. Min Act: -0.0000

Data Index: 867678 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8065. Min Act: -0.0000

Data Index: 185372 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.7959. Min Act: -0.0001

Data Index: 991092 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.7733. Min Act: -0.0001

Data Index: 95644 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.8666. Min Act: -0.0000

Data Index: 635945 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.5842. Min Act: -0.0001

Data Index: 723455 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.9612. Min Act: -0.0001

Data Index: 667354 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 2.2358. Min Range: -2.2358

Max Act: 1.7600. Min Act: -0.0001

Data Index: 1137147 (C4 (Web Text))

Max Activating Token Index: 23