Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 210 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.8555. Min Act: -0.0001

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.8166. Min Act: -0.0000

Data Index: 643835 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7575. Min Act: -0.0001

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6777. Min Act: -0.0000

Data Index: 202218 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6924. Min Act: -0.0001

Data Index: 805854 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5793. Min Act: -0.0001

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6758. Min Act: -0.0000

Data Index: 955438 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6126. Min Act: -0.0001

Data Index: 797332 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5793. Min Act: -0.0001

Data Index: 732017 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5760. Min Act: -0.0001

Data Index: 687631 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5768. Min Act: -0.0001

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5867. Min Act: -0.0001

Data Index: 230797 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1416091 (Python Code)

Max Activating Token Index: 757

Text #13

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5991. Min Act: -0.0000

Data Index: 635655 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5668. Min Act: -0.0001

Data Index: 1581321 (Python Code)

Max Activating Token Index: 722

Text #15

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5748. Min Act: -0.0001

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.5418. Min Act: -0.0001

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.4702. Min Act: -0.0001

Data Index: 468938 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.4907. Min Act: -0.0001

Data Index: 577346 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.4980. Min Act: -0.0000

Data Index: 734061 (C4 (Web Text))

Max Activating Token Index: 258