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

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

Neuron 2185 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: 0.3761. Min Range: -0.3761

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1185574 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2975. Min Act: -0.0001

Data Index: 711283 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2785. Min Act: -0.0001

Data Index: 628212 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2986. Min Act: -0.0001

Data Index: 647427 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2871. Min Act: -0.0001

Data Index: 496696 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2760. Min Act: -0.0001

Data Index: 508020 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1187618 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2641. Min Act: -0.0001

Data Index: 348681 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2677. Min Act: -0.0001

Data Index: 316458 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2412. Min Act: -0.0001

Data Index: 279670 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1148885 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2527. Min Act: -0.0001

Data Index: 95764 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2291. Min Act: -0.0001

Data Index: 924629 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2310. Min Act: -0.0001

Data Index: 529211 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2317. Min Act: -0.0001

Data Index: 225720 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2394. Min Act: -0.0001

Data Index: 493269 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.1907. Min Act: -0.0001

Data Index: 117313 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2266. Min Act: -0.0001

Data Index: 827075 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2074. Min Act: -0.0001

Data Index: 746559 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1292013 (C4 (Web Text))

Max Activating Token Index: 418