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

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

Neuron 2341 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: 1.9495. Min Range: -1.9495

Max Act: 1.9495. Min Act: -0.0000

Data Index: 503787 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1305856 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3886. Min Act: -0.0000

Data Index: 26859 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3461. Min Act: -0.0000

Data Index: 984235 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3357. Min Act: -0.0000

Data Index: 42351 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3378. Min Act: -0.0000

Data Index: 687803 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.1928. Min Act: -0.0000

Data Index: 232710 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.2643. Min Act: -0.0000

Data Index: 335119 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.1136. Min Act: -0.0000

Data Index: 403929 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.1175. Min Act: -0.0000

Data Index: 619727 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.1805. Min Act: -0.0000

Data Index: 577556 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1007162 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3103. Min Act: -0.0000

Data Index: 790388 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.1486. Min Act: -0.0000

Data Index: 739259 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.9495. Min Range: -1.9495

Max Act: 0.9934. Min Act: -0.0000

Data Index: 425105 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.2772. Min Act: -0.0000

Data Index: 138281 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3377. Min Act: -0.0000

Data Index: 1084019 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.1194. Min Act: -0.0000

Data Index: 981269 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.2381. Min Act: -0.0000

Data Index: 843588 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 1.9495. Min Range: -1.9495

Max Act: 1.3132. Min Act: -0.0000

Data Index: 607212 (C4 (Web Text))

Max Activating Token Index: 534