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

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

Neuron 2858 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8422. Min Range: -3.8422

Max Act: 3.8422. Min Act: -0.0000

Data Index: 347099 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.9165. Min Act: -0.0000

Data Index: 1140955 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 3.8422. Min Range: -3.8422

Max Act: 3.2688. Min Act: -0.0000

Data Index: 160279 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.7281. Min Act: -0.0000

Data Index: 1311100 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.7237. Min Act: -0.0000

Data Index: 1129627 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.7457. Min Act: -0.0000

Data Index: 824069 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.6982. Min Act: -0.0000

Data Index: 42749 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.3554. Min Act: -0.0000

Data Index: 283359 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.3067. Min Act: -0.0000

Data Index: 1219147 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.5084. Min Act: -0.0000

Data Index: 891945 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.2202. Min Act: -0.0000

Data Index: 199942 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.8422. Min Range: -3.8422

Max Act: 1.9666. Min Act: -0.0000

Data Index: 1091632 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.1591. Min Act: -0.0000

Data Index: 959107 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.1036. Min Act: -0.0000

Data Index: 1244890 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.2080. Min Act: -0.0000

Data Index: 1222099 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.0842. Min Act: -0.0000

Data Index: 15965 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.8422. Min Range: -3.8422

Max Act: 1.9874. Min Act: -0.0000

Data Index: 5673 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.1922. Min Act: -0.0000

Data Index: 820489 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.0650. Min Act: -0.0000

Data Index: 424691 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 3.8422. Min Range: -3.8422

Max Act: 2.0612. Min Act: -0.0000

Data Index: 1218548 (C4 (Web Text))

Max Activating Token Index: 525