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

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

Neuron 5172 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.3819. Min Act: -0.0000

Data Index: 674291 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.3604. Min Act: -0.0000

Data Index: 978775 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.4425. Min Act: -0.0000

Data Index: 262234 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.4119. Min Act: -0.0000

Data Index: 421779 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.4373. Min Act: -0.0000

Data Index: 758768 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1197849 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.2573. Min Act: -0.0000

Data Index: 996517 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1671. Min Act: -0.0000

Data Index: 380569 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.2293. Min Act: -0.0000

Data Index: 662571 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1316. Min Act: -0.0000

Data Index: 548725 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1891. Min Act: -0.0000

Data Index: 900387 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1332. Min Act: -0.0000

Data Index: 359160 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1588. Min Act: -0.0000

Data Index: 125969 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.4425. Min Range: -1.4425

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1317488 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1812. Min Act: -0.0000

Data Index: 291400 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1881. Min Act: -0.0000

Data Index: 79589 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1027972 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1298637 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.0601. Min Act: -0.0000

Data Index: 832761 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.4425. Min Range: -1.4425

Max Act: 1.0642. Min Act: -0.0000

Data Index: 41835 (C4 (Web Text))

Max Activating Token Index: 79