Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1463 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4232. Min Act: -0.0002

Data Index: 1283261 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4310. Min Act: -0.0001

Data Index: 707505 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.5685. Min Act: -0.0002

Data Index: 759712 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.2348. Min Act: -0.0001

Data Index: 408316 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.9540. Min Act: -0.0002

Data Index: 1091734 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.6718. Min Act: -0.0002

Data Index: 556954 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.7951. Min Act: -0.0002

Data Index: 971032 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.7404. Min Act: -0.0001

Data Index: 367166 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.7765. Min Act: -0.0002

Data Index: 710021 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.6337. Min Act: -0.0001

Data Index: 125985 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.6865. Min Act: -0.0001

Data Index: 571196 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.3839. Min Act: -0.0001

Data Index: 365662 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.7167. Min Act: -0.0001

Data Index: 998980 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.4748. Min Act: -0.0002

Data Index: 619432 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.1742. Min Act: -0.0002

Data Index: 45305 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.3582. Min Act: -0.0001

Data Index: 739738 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.2823. Min Act: -0.0002

Data Index: 1069247 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.2663. Min Act: -0.0001

Data Index: 77564 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.2582. Min Act: -0.0001

Data Index: 285813 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.5685. Min Range: -3.5685

Max Act: 2.3790. Min Act: -0.0002

Data Index: 378767 (C4 (Web Text))

Max Activating Token Index: 146