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

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

Neuron 1850 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1296060 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2998. Min Act: -0.0000

Data Index: 396867 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2725. Min Act: -0.0000

Data Index: 563846 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2638. Min Act: -0.0000

Data Index: 801544 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2710. Min Act: -0.0000

Data Index: 630858 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2772. Min Act: -0.0000

Data Index: 393302 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2622. Min Act: -0.0000

Data Index: 404184 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2694. Min Act: -0.0001

Data Index: 347950 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2694. Min Act: -0.0000

Data Index: 612136 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2663. Min Act: -0.0000

Data Index: 136450 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2529. Min Act: -0.0000

Data Index: 61363 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2360. Min Act: -0.0000

Data Index: 862973 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1260924 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2427. Min Act: -0.0001

Data Index: 93739 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2388. Min Act: -0.0000

Data Index: 648467 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2474. Min Act: -0.0000

Data Index: 912106 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2397. Min Act: -0.0000

Data Index: 508430 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2361. Min Act: -0.0000

Data Index: 473908 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2526. Min Act: -0.0000

Data Index: 901713 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2358. Min Act: -0.0000

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 117