Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1973 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.1773. Min Act: -0.0000

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.1166. Min Act: -0.0000

Data Index: 740822 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1133858 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9981. Min Act: -0.0000

Data Index: 510085 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9610. Min Act: -0.0000

Data Index: 691478 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9890. Min Act: -0.0000

Data Index: 960210 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9257. Min Act: -0.0000

Data Index: 127432 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9120. Min Act: -0.0000

Data Index: 787170 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9068. Min Act: -0.0000

Data Index: 705198 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9200. Min Act: -0.0000

Data Index: 310024 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9343. Min Act: -0.0000

Data Index: 212810 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1071959 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8630. Min Act: -0.0000

Data Index: 467131 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1081821 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8900. Min Act: -0.0000

Data Index: 581758 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8583. Min Act: -0.0000

Data Index: 156826 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8834. Min Act: -0.0000

Data Index: 796520 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1003550 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8947. Min Act: -0.0000

Data Index: 3299 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8372. Min Act: -0.0000

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 535