Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.8812. Min Act: -0.0001

Data Index: 1199245 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7765. Min Act: -0.0001

Data Index: 412363 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7742. Min Act: -0.0001

Data Index: 784956 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.9287. Min Act: -0.0001

Data Index: 56333 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.9164. Min Act: -0.0001

Data Index: 439923 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7671. Min Act: -0.0001

Data Index: 108767 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.8225. Min Act: -0.0001

Data Index: 1227141 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7640. Min Act: -0.0001

Data Index: 1243927 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7199. Min Act: -0.0001

Data Index: 878939 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.6435. Min Act: -0.0001

Data Index: 406947 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.8056. Min Act: -0.0001

Data Index: 390622 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.6368. Min Act: -0.0001

Data Index: 599684 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.5887. Min Act: -0.0001

Data Index: 729335 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7060. Min Act: -0.0001

Data Index: 568223 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7525. Min Act: -0.0001

Data Index: 433748 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.5484. Min Act: -0.0001

Data Index: 1012913 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7271. Min Act: -0.0001

Data Index: 1209936 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.5401. Min Act: -0.0001

Data Index: 1354487 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.4445. Min Act: -0.0001

Data Index: 449962 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.3974. Min Act: -0.0001

Data Index: 448422 (C4 (Web Text))

Max Activating Token Index: 596