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

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

Neuron 100 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1646588 (Python Code)

Max Activating Token Index: 466

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1117. Min Act: -0.0001

Data Index: 355548 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0976. Min Act: -0.0001

Data Index: 597098 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0837. Min Act: -0.0001

Data Index: 214422 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0889. Min Act: -0.0001

Data Index: 457553 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1632039 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1469768 (Python Code)

Max Activating Token Index: 244

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1510498 (Python Code)

Max Activating Token Index: 899

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1219350 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1537190 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1008627 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1067. Min Act: -0.0001

Data Index: 221788 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1211320 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1459324 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0923. Min Act: -0.0001

Data Index: 293987 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1386314 (Python Code)

Max Activating Token Index: 829

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0786. Min Act: -0.0001

Data Index: 261023 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0805. Min Act: -0.0001

Data Index: 60351 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0875. Min Act: -0.0001

Data Index: 287640 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1473701 (Python Code)

Max Activating Token Index: 678