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

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

Neuron 2097 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2623. Min Range: -2.2623

Max Act: 2.2623. Min Act: -0.0000

Data Index: 619978 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 2.2623. Min Range: -2.2623

Max Act: 2.0805. Min Act: -0.0000

Data Index: 1107549 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.9654. Min Act: -0.0000

Data Index: 1488729 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 2.2623. Min Range: -2.2623

Max Act: 2.0779. Min Act: -0.0000

Data Index: 794424 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.8428. Min Act: -0.0000

Data Index: 321732 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.8807. Min Act: -0.0000

Data Index: 1453114 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.8533. Min Act: -0.0000

Data Index: 51201 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.6902. Min Act: -0.0000

Data Index: 130780 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.5998. Min Act: -0.0000

Data Index: 1574088 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.6156. Min Act: -0.0000

Data Index: 628259 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.4846. Min Act: -0.0000

Data Index: 339155 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.4643. Min Act: -0.0000

Data Index: 378031 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.4158. Min Act: -0.0000

Data Index: 409059 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1609452 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.8187. Min Act: -0.0000

Data Index: 70293 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.4863. Min Act: -0.0000

Data Index: 1301800 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.5941. Min Act: -0.0000

Data Index: 262212 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.4489. Min Act: -0.0000

Data Index: 974644 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.3714. Min Act: -0.0000

Data Index: 159148 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 2.2623. Min Range: -2.2623

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1194007 (C4 (Web Text))

Max Activating Token Index: 187