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

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

Neuron 2881 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1062983 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0945. Min Act: -0.0003

Data Index: 595963 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0898. Min Act: -0.0003

Data Index: 594697 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0876. Min Act: -0.0003

Data Index: 797425 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0875. Min Act: -0.0003

Data Index: 409069 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0806. Min Act: -0.0003

Data Index: 902248 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0791. Min Act: -0.0003

Data Index: 1410617 (Python Code)

Max Activating Token Index: 926

Text #7

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1599026 (Python Code)

Max Activating Token Index: 265

Text #8

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1506860 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0791. Min Act: -0.0003

Data Index: 194045 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0820. Min Act: -0.0003

Data Index: 404345 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0789. Min Act: -0.0003

Data Index: 348617 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1542699 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0817. Min Act: -0.0003

Data Index: 1342330 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1573864 (Python Code)

Max Activating Token Index: 231

Text #15

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0814. Min Act: -0.0003

Data Index: 706054 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0740. Min Act: -0.0003

Data Index: 1444175 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0815. Min Act: -0.0003

Data Index: 323167 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0804. Min Act: -0.0003

Data Index: 489582 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1445930 (Python Code)

Max Activating Token Index: 773