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

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

Neuron 399 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: 1.3260. Min Range: -1.3260

Max Act: 1.3260. Min Act: -0.0001

Data Index: 1136946 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.2287. Min Act: -0.0001

Data Index: 179120 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.3203. Min Act: -0.0000

Data Index: 834147 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.2299. Min Act: -0.0001

Data Index: 765530 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.2072. Min Act: -0.0001

Data Index: 138394 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0967. Min Act: -0.0000

Data Index: 476463 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.1078. Min Act: -0.0000

Data Index: 692281 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1027350 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0574. Min Act: -0.0001

Data Index: 880165 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0862. Min Act: -0.0001

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9438. Min Act: -0.0001

Data Index: 1085282 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9398. Min Act: -0.0001

Data Index: 264740 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0356. Min Act: -0.0000

Data Index: 900384 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0316. Min Act: -0.0000

Data Index: 46537 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0703. Min Act: -0.0001

Data Index: 1257946 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0280. Min Act: -0.0001

Data Index: 193497 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9864. Min Act: -0.0001

Data Index: 1084127 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0208. Min Act: -0.0000

Data Index: 833556 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0199. Min Act: -0.0001

Data Index: 814382 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.8012. Min Act: -0.0001

Data Index: 952436 (C4 (Web Text))

Max Activating Token Index: 157