Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 286 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.5094. Min Act: -0.0000

Data Index: 245375 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1204693 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3749. Min Act: -0.0000

Data Index: 699444 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3882. Min Act: -0.0000

Data Index: 28049 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3742. Min Act: -0.0000

Data Index: 301881 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3697. Min Act: -0.0000

Data Index: 153064 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1459017 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2829. Min Act: -0.0000

Data Index: 567864 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2996. Min Act: -0.0000

Data Index: 563506 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1039556 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2906. Min Act: -0.0000

Data Index: 373539 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3053. Min Act: -0.0000

Data Index: 279862 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2543. Min Act: -0.0000

Data Index: 893353 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1441823 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2813. Min Act: -0.0000

Data Index: 552761 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2841. Min Act: -0.0000

Data Index: 599599 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1368099 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1010741 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1362062 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2420. Min Act: -0.0000

Data Index: 351239 (C4 (Web Text))

Max Activating Token Index: 744