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

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

Neuron 3929 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4810. Min Act: -0.0002

Data Index: 633951 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4903. Min Act: -0.0001

Data Index: 325115 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4864. Min Act: -0.0001

Data Index: 1174206 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4498. Min Act: -0.0002

Data Index: 641521 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4655. Min Act: -0.0001

Data Index: 482890 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4497. Min Act: -0.0001

Data Index: 781870 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4557. Min Act: -0.0001

Data Index: 594159 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4439. Min Act: -0.0002

Data Index: 535158 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4414. Min Act: -0.0002

Data Index: 314891 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4489. Min Act: -0.0001

Data Index: 218831 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4360. Min Act: -0.0001

Data Index: 312401 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4795. Min Act: -0.0001

Data Index: 414599 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4034. Min Act: -0.0002

Data Index: 787435 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4266. Min Act: -0.0002

Data Index: 596994 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3926. Min Act: -0.0001

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4129. Min Act: -0.0001

Data Index: 1089544 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4491. Min Act: -0.0001

Data Index: 227040 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4129. Min Act: -0.0002

Data Index: 105193 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4239. Min Act: -0.0001

Data Index: 461916 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4485. Min Act: -0.0002

Data Index: 287476 (C4 (Web Text))

Max Activating Token Index: 565