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

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

Neuron 689 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.5152. Min Act: -0.0001

Data Index: 636075 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.4220. Min Act: -0.0001

Data Index: 1257147 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.4245. Min Act: -0.0001

Data Index: 790213 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.5290. Min Act: -0.0001

Data Index: 261696 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3434. Min Act: -0.0001

Data Index: 82993 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3440. Min Act: -0.0001

Data Index: 604332 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3110. Min Act: -0.0001

Data Index: 301333 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3360. Min Act: -0.0000

Data Index: 528484 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3418. Min Act: -0.0001

Data Index: 1119225 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2760. Min Act: -0.0001

Data Index: 461106 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2777. Min Act: -0.0001

Data Index: 1295944 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2716. Min Act: -0.0001

Data Index: 887027 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2313. Min Act: -0.0001

Data Index: 1314505 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1304682 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3818. Min Act: -0.0000

Data Index: 424590 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2230. Min Act: -0.0001

Data Index: 604177 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.1420. Min Act: -0.0001

Data Index: 186780 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.1502. Min Act: -0.0001

Data Index: 1075474 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.1252. Min Act: -0.0001

Data Index: 584406 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.1544. Min Act: -0.0001

Data Index: 166502 (C4 (Web Text))

Max Activating Token Index: 416