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

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

Neuron 4958 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.1553. Min Act: -0.0000

Data Index: 1011160 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.1940. Min Act: -0.0000

Data Index: 667908 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9451. Min Act: -0.0000

Data Index: 611208 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.0145. Min Act: -0.0000

Data Index: 573129 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.0304. Min Act: -0.0000

Data Index: 127335 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.1195. Min Act: -0.0000

Data Index: 592963 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.1450. Min Act: -0.0000

Data Index: 590267 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1306933 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9980. Min Act: -0.0000

Data Index: 371441 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.0251. Min Act: -0.0000

Data Index: 160344 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.0018. Min Act: -0.0000

Data Index: 945507 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1091519 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1333713 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8918. Min Act: -0.0000

Data Index: 265295 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1003654 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7980. Min Act: -0.0001

Data Index: 497291 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8289. Min Act: -0.0000

Data Index: 704992 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1051588 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1065066 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8450. Min Act: -0.0000

Data Index: 342472 (C4 (Web Text))

Max Activating Token Index: 682