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

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

Neuron 5646 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: 0.2589. Min Range: -0.2589

Max Act: 0.2486. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2589. Min Act: -0.0000

Data Index: 325211 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1394654 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1034610 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2058. Min Act: -0.0000

Data Index: 57723 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2249. Min Act: -0.0000

Data Index: 922376 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2231. Min Act: -0.0000

Data Index: 452533 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2543. Min Act: -0.0000

Data Index: 754361 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2084. Min Act: -0.0000

Data Index: 231846 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2163. Min Act: -0.0000

Data Index: 89479 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2159. Min Act: -0.0000

Data Index: 695156 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1211554 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1934. Min Act: -0.0000

Data Index: 732722 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1935. Min Act: -0.0000

Data Index: 485074 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1585297 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1288577 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1691. Min Act: -0.0000

Data Index: 642694 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1235461 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1603659 (Python Code)

Max Activating Token Index: 674