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

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

Neuron 160 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6841. Min Act: -0.0001

Data Index: 792864 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6495. Min Act: -0.0000

Data Index: 791056 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5182. Min Act: -0.0000

Data Index: 541805 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4983. Min Act: -0.0001

Data Index: 965748 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4896. Min Act: -0.0000

Data Index: 909343 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4868. Min Act: -0.0000

Data Index: 777197 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4978. Min Act: 0.0001

Data Index: 645957 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4840. Min Act: 0.0000

Data Index: 90573 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5091. Min Act: -0.0000

Data Index: 491882 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4732. Min Act: -0.0001

Data Index: 632293 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4824. Min Act: -0.0001

Data Index: 1175968 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4719. Min Act: -0.0000

Data Index: 225610 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4684. Min Act: -0.0000

Data Index: 150880 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4711. Min Act: -0.0001

Data Index: 230551 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4688. Min Act: -0.0000

Data Index: 456495 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4681. Min Act: -0.0000

Data Index: 382834 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1052057 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4626. Min Act: -0.0001

Data Index: 556025 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4619. Min Act: -0.0000

Data Index: 132876 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1092148 (C4 (Web Text))

Max Activating Token Index: 587