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

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

Neuron 5168 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5326. Min Act: -0.0000

Data Index: 199996 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5088. Min Act: -0.0000

Data Index: 426086 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4760. Min Act: -0.0000

Data Index: 777362 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1016833 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4356. Min Act: -0.0000

Data Index: 586511 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1097249 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1016022 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1216623 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4345. Min Act: -0.0000

Data Index: 299489 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4206. Min Act: -0.0000

Data Index: 697084 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4135. Min Act: -0.0000

Data Index: 477950 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4116. Min Act: -0.0000

Data Index: 963859 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.3938. Min Act: -0.0000

Data Index: 264369 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4232. Min Act: -0.0000

Data Index: 280907 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.3923. Min Act: -0.0000

Data Index: 216598 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4207. Min Act: -0.0000

Data Index: 446481 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1320929 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.3988. Min Act: -0.0000

Data Index: 237037 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4247. Min Act: -0.0000

Data Index: 55464 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4093. Min Act: -0.0000

Data Index: 548759 (C4 (Web Text))

Max Activating Token Index: 913