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

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

Neuron 1369 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1024422 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.4230. Min Act: -0.0000

Data Index: 687529 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.3504. Min Act: -0.0000

Data Index: 126036 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1100607 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.2977. Min Act: -0.0000

Data Index: 360119 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1276383 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.3180. Min Act: -0.0000

Data Index: 1018381 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1890. Min Act: -0.0000

Data Index: 808861 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.2133. Min Act: -0.0000

Data Index: 378951 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.2034. Min Act: -0.0000

Data Index: 990836 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1042849 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1263. Min Act: -0.0000

Data Index: 116150 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1241. Min Act: -0.0000

Data Index: 473967 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1185. Min Act: -0.0000

Data Index: 63856 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1585. Min Act: -0.0000

Data Index: 560125 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1229. Min Act: -0.0000

Data Index: 850280 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1062621 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.0662. Min Act: -0.0000

Data Index: 564891 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1220. Min Act: -0.0000

Data Index: 824221 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.6938. Min Range: -1.6938

Max Act: 1.1165. Min Act: -0.0000

Data Index: 635364 (C4 (Web Text))

Max Activating Token Index: 153