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

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

Neuron 1188 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.4068. Min Act: -0.0000

Data Index: 544136 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.4255. Min Act: -0.0000

Data Index: 898414 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2756. Min Act: 0.0000

Data Index: 279329 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2563. Min Act: -0.0000

Data Index: 311715 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2937. Min Act: -0.0000

Data Index: 510359 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.1529. Min Act: -0.0000

Data Index: 500303 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0775. Min Act: -0.0000

Data Index: 423236 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0625. Min Act: -0.0000

Data Index: 348882 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0335. Min Act: -0.0000

Data Index: 72626 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9888. Min Act: 0.0001

Data Index: 850258 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9659. Min Act: -0.0000

Data Index: 772275 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9759. Min Act: 0.0000

Data Index: 60607 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1048243 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9555. Min Act: 0.0001

Data Index: 1162731 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9757. Min Act: -0.0000

Data Index: 312012 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9996. Min Act: 0.0000

Data Index: 1180501 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9403. Min Act: -0.0000

Data Index: 493123 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.8796. Min Act: 0.0001

Data Index: 357313 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9002. Min Act: 0.0001

Data Index: 1092932 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.8157. Min Act: -0.0000

Data Index: 480920 (C4 (Web Text))

Max Activating Token Index: 99