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

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

Neuron 1401 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: 2.5556. Min Range: -2.5556

Max Act: 2.5556. Min Act: -0.0000

Data Index: 638823 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.6437. Min Act: -0.0000

Data Index: 165710 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.7243. Min Act: -0.0000

Data Index: 529160 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.5235. Min Act: -0.0000

Data Index: 86875 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.5607. Min Act: -0.0000

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.6179. Min Act: -0.0000

Data Index: 842611 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.4942. Min Act: -0.0000

Data Index: 15654 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.4973. Min Act: -0.0000

Data Index: 138013 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.4167. Min Act: -0.0000

Data Index: 802972 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.4936. Min Act: -0.0000

Data Index: 956627 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.5096. Min Act: -0.0000

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.5136. Min Act: -0.0000

Data Index: 926917 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1623715 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.3816. Min Act: -0.0000

Data Index: 802685 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.2836. Min Act: -0.0000

Data Index: 241826 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1146757 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1126598 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.3716. Min Act: -0.0000

Data Index: 241284 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.3946. Min Act: -0.0000

Data Index: 460322 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 2.5556. Min Range: -2.5556

Max Act: 1.3516. Min Act: -0.0000

Data Index: 279304 (C4 (Web Text))

Max Activating Token Index: 106