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

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

Neuron 3709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2314. Min Range: -3.2314

Max Act: 3.2277. Min Act: -0.0000

Data Index: 147998 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 3.2314. Min Range: -3.2314

Max Act: 3.2314. Min Act: -0.0000

Data Index: 900398 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.7769. Min Act: -0.0000

Data Index: 1165885 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.7063. Min Act: -0.0000

Data Index: 1266945 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.9412. Min Act: -0.0000

Data Index: 482073 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.7693. Min Act: -0.0000

Data Index: 1231201 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.7555. Min Act: -0.0000

Data Index: 1306158 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.7782. Min Act: -0.0000

Data Index: 886946 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.6835. Min Act: -0.0000

Data Index: 1186453 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.6665. Min Act: -0.0000

Data Index: 875043 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1204025 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.6608. Min Act: -0.0000

Data Index: 995769 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.5377. Min Act: -0.0000

Data Index: 703773 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.5126. Min Act: -0.0000

Data Index: 864459 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.5218. Min Act: -0.0000

Data Index: 676861 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.4091. Min Act: -0.0000

Data Index: 1001359 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.4805. Min Act: -0.0000

Data Index: 1211669 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.5086. Min Act: -0.0000

Data Index: 508173 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.4551. Min Act: -0.0000

Data Index: 384320 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.2314. Min Range: -3.2314

Max Act: 2.5824. Min Act: -0.0000

Data Index: 909329 (C4 (Web Text))

Max Activating Token Index: 791