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

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

Neuron 696 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: 2.5659. Min Range: -2.5659

Max Act: 2.5659. Min Act: -0.0000

Data Index: 394003 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.5031. Min Act: -0.0000

Data Index: 911622 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.3996. Min Act: -0.0000

Data Index: 1192529 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.4776. Min Act: -0.0000

Data Index: 730773 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.3387. Min Act: -0.0000

Data Index: 478647 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.4370. Min Act: -0.0000

Data Index: 259384 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.5410. Min Act: -0.0000

Data Index: 479230 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.2935. Min Act: -0.0000

Data Index: 84585 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1692. Min Act: -0.0000

Data Index: 15036 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1594. Min Act: -0.0000

Data Index: 282767 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.2550. Min Act: -0.0000

Data Index: 559880 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1433. Min Act: -0.0000

Data Index: 1071639 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1336. Min Act: -0.0000

Data Index: 1294091 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1236. Min Act: -0.0000

Data Index: 584849 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1131. Min Act: -0.0000

Data Index: 528023 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.0574. Min Act: -0.0000

Data Index: 202642 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1666. Min Act: -0.0000

Data Index: 580885 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.4303. Min Act: -0.0000

Data Index: 1312583 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.2771. Min Act: -0.0000

Data Index: 1013020 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 2.5659. Min Range: -2.5659

Max Act: 2.1344. Min Act: -0.0000

Data Index: 1022525 (C4 (Web Text))

Max Activating Token Index: 566