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

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

Neuron 3628 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.4620. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.4502. Min Act: -0.0000

Data Index: 1599664 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.4198. Min Act: -0.0000

Data Index: 737507 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.2647. Min Act: -0.0000

Data Index: 929508 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.1268. Min Act: -0.0000

Data Index: 859628 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.1169. Min Act: -0.0000

Data Index: 1531613 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.1913. Min Act: -0.0000

Data Index: 239887 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.9543. Min Act: -0.0000

Data Index: 611783 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 2.4620. Min Range: -2.4620

Max Act: 2.0284. Min Act: -0.0000

Data Index: 728518 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.9613. Min Act: -0.0000

Data Index: 1234252 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.8835. Min Act: -0.0000

Data Index: 1595784 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.9560. Min Act: -0.0000

Data Index: 866774 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.9204. Min Act: -0.0000

Data Index: 353996 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.8954. Min Act: -0.0000

Data Index: 707124 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.6789. Min Act: -0.0000

Data Index: 1030650 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.9796. Min Act: -0.0000

Data Index: 1162766 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.7677. Min Act: -0.0000

Data Index: 473792 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.8425. Min Act: -0.0000

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.7344. Min Act: -0.0000

Data Index: 941106 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 2.4620. Min Range: -2.4620

Max Act: 1.8425. Min Act: -0.0000

Data Index: 975864 (C4 (Web Text))

Max Activating Token Index: 448