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

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

Neuron 3555 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: 2.4675. Min Range: -2.4675

Max Act: 2.4675. Min Act: -0.0000

Data Index: 52010 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 2.4675. Min Range: -2.4675

Max Act: 2.3260. Min Act: -0.0000

Data Index: 325738 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 2.4675. Min Range: -2.4675

Max Act: 2.1046. Min Act: -0.0000

Data Index: 1124958 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.9746. Min Act: -0.0000

Data Index: 1054737 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.9803. Min Act: -0.0000

Data Index: 85041 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 2.4675. Min Range: -2.4675

Max Act: 2.0594. Min Act: -0.0000

Data Index: 745233 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.8240. Min Act: -0.0000

Data Index: 632478 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.9316. Min Act: -0.0000

Data Index: 869792 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1156567 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7753. Min Act: -0.0000

Data Index: 401361 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.8387. Min Act: -0.0000

Data Index: 146686 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.8332. Min Act: -0.0000

Data Index: 694731 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.8286. Min Act: -0.0000

Data Index: 506906 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.6183. Min Act: -0.0000

Data Index: 568295 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.6837. Min Act: -0.0000

Data Index: 798861 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.8919. Min Act: -0.0000

Data Index: 515997 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.6767. Min Act: -0.0000

Data Index: 884028 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7779. Min Act: -0.0000

Data Index: 814495 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7403. Min Act: -0.0000

Data Index: 940019 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.5532. Min Act: -0.0000

Data Index: 977304 (C4 (Web Text))

Max Activating Token Index: 591