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

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

Neuron 2630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1280. Min Act: -0.0004

Data Index: 1342971 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0862. Min Act: -0.0004

Data Index: 1148043 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0876. Min Act: -0.0004

Data Index: 1135879 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0897. Min Act: -0.0004

Data Index: 767678 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0721. Min Act: -0.0004

Data Index: 213938 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0873. Min Act: -0.0004

Data Index: 860897 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0900. Min Act: -0.0004

Data Index: 90709 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0842. Min Act: -0.0004

Data Index: 1359227 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0804. Min Act: -0.0004

Data Index: 1242411 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0832. Min Act: -0.0004

Data Index: 398493 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0831. Min Act: -0.0004

Data Index: 21818 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0669. Min Act: -0.0004

Data Index: 330092 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1418536 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0804. Min Act: -0.0004

Data Index: 520713 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0808. Min Act: -0.0004

Data Index: 1138962 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0777. Min Act: -0.0004

Data Index: 301100 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0614. Min Act: -0.0004

Data Index: 1170546 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0829. Min Act: -0.0004

Data Index: 602543 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0796. Min Act: -0.0004

Data Index: 772953 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0661. Min Act: -0.0004

Data Index: 66044 (C4 (Web Text))

Max Activating Token Index: 639