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

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

Neuron 2461 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: 1.9111. Min Range: -1.9111

Max Act: 1.9111. Min Act: -0.0000

Data Index: 510389 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.4683. Min Act: -0.0000

Data Index: 873317 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.6239. Min Act: -0.0000

Data Index: 443145 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.3125. Min Act: -0.0000

Data Index: 988767 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.3924. Min Act: -0.0000

Data Index: 1203812 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.3742. Min Act: -0.0000

Data Index: 964232 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.2779. Min Act: -0.0000

Data Index: 513157 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1208867 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1009527 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1153016 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.2315. Min Act: -0.0000

Data Index: 20141 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.1780. Min Act: -0.0000

Data Index: 247422 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.1106. Min Act: -0.0000

Data Index: 428963 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.1580. Min Act: -0.0000

Data Index: 976391 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.1822. Min Act: -0.0000

Data Index: 8713 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1590786 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.0422. Min Act: -0.0000

Data Index: 233796 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.1679. Min Act: -0.0000

Data Index: 311955 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1078145 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.9111. Min Range: -1.9111

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1367760 (Python Code)

Max Activating Token Index: 902