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

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

Neuron 2870 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.9587. Min Act: -0.0000

Data Index: 1229819 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.3857. Min Act: -0.0000

Data Index: 1041829 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.1889. Min Act: -0.0000

Data Index: 132935 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.2684. Min Act: -0.0000

Data Index: 953538 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.0410. Min Act: -0.0000

Data Index: 546930 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.1497. Min Act: -0.0000

Data Index: 133856 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.1353. Min Act: -0.0000

Data Index: 1245931 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.8632. Min Act: -0.0000

Data Index: 958924 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 3.9587. Min Range: -3.9587

Max Act: 3.0134. Min Act: -0.0000

Data Index: 732184 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.7215. Min Act: -0.0000

Data Index: 69968 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.4400. Min Act: -0.0000

Data Index: 507532 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.7060. Min Act: -0.0000

Data Index: 622285 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.5585. Min Act: -0.0000

Data Index: 1059856 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.6449. Min Act: -0.0000

Data Index: 1243130 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.5245. Min Act: -0.0000

Data Index: 510891 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.4667. Min Act: -0.0000

Data Index: 1310105 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.4280. Min Act: -0.0000

Data Index: 498295 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.5169. Min Act: -0.0000

Data Index: 734378 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.3823. Min Act: -0.0000

Data Index: 170352 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 3.9587. Min Range: -3.9587

Max Act: 2.5860. Min Act: -0.0000

Data Index: 581452 (C4 (Web Text))

Max Activating Token Index: 789