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

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

Neuron 2095 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1482. Min Act: -0.0002

Data Index: 547385 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.8119. Min Act: -0.0002

Data Index: 740571 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 3.1482. Min Range: -3.1482

Max Act: 2.6951. Min Act: -0.0002

Data Index: 728800 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 3.1482. Min Range: -3.1482

Max Act: 2.1071. Min Act: -0.0002

Data Index: 537252 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 3.1482. Min Range: -3.1482

Max Act: 0.9351. Min Act: -0.0002

Data Index: 1021127 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.5040. Min Act: -0.0002

Data Index: 596994 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.8692. Min Act: -0.0002

Data Index: 534482 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 3.1482. Min Range: -3.1482

Max Act: 0.6491. Min Act: -0.0002

Data Index: 1186597 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.9134. Min Act: -0.0002

Data Index: 46008 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 3.1482. Min Range: -3.1482

Max Act: 2.2201. Min Act: -0.0002

Data Index: 732121 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.0132. Min Act: -0.0002

Data Index: 578301 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.3097. Min Act: -0.0002

Data Index: 690789 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 3.1482. Min Range: -3.1482

Max Act: 2.1663. Min Act: -0.0002

Data Index: 1034597 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 3.1482. Min Range: -3.1482

Max Act: 2.2832. Min Act: -0.0002

Data Index: 940063 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.4261. Min Act: -0.0002

Data Index: 77212 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 3.1482. Min Range: -3.1482

Max Act: 2.6875. Min Act: -0.0002

Data Index: 483271 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 3.1482. Min Range: -3.1482

Max Act: 2.3192. Min Act: -0.0002

Data Index: 217162 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 3.1482. Min Range: -3.1482

Max Act: 1.7253. Min Act: -0.0002

Data Index: 1218968 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.1482. Min Range: -3.1482

Max Act: 0.8141. Min Act: -0.0002

Data Index: 986555 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 3.1482. Min Range: -3.1482

Max Act: 0.6444. Min Act: -0.0002

Data Index: 627445 (C4 (Web Text))

Max Activating Token Index: 311