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

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

Neuron 2635 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.7389. Min Act: -0.0000

Data Index: 28157 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6663. Min Act: -0.0000

Data Index: 751979 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1122039 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6505. Min Act: -0.0000

Data Index: 633447 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6416. Min Act: -0.0000

Data Index: 407294 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5227. Min Act: -0.0000

Data Index: 439254 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4991. Min Act: -0.0000

Data Index: 725585 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1008102 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4740. Min Act: -0.0000

Data Index: 440021 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1162951 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4698. Min Act: -0.0000

Data Index: 180358 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4596. Min Act: -0.0000

Data Index: 172870 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4327. Min Act: -0.0000

Data Index: 81797 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1028705 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1163336 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4218. Min Act: -0.0000

Data Index: 281802 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4209. Min Act: -0.0000

Data Index: 781125 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4010. Min Act: -0.0000

Data Index: 314531 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4914. Min Act: -0.0000

Data Index: 22995 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4166. Min Act: 0.0000

Data Index: 270024 (C4 (Web Text))

Max Activating Token Index: 214