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

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

Neuron 3235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.6661. Min Act: -0.0000

Data Index: 1194502 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.5824. Min Act: -0.0000

Data Index: 884793 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.3946. Min Act: -0.0000

Data Index: 1080361 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.3715. Min Act: -0.0000

Data Index: 877490 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.3512. Min Act: -0.0000

Data Index: 395451 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.3280. Min Act: -0.0000

Data Index: 1349861 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.2483. Min Act: -0.0000

Data Index: 603779 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.3684. Min Act: -0.0000

Data Index: 989195 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.4720. Min Act: -0.0000

Data Index: 1051422 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.2784. Min Act: -0.0000

Data Index: 1048465 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.1864. Min Act: -0.0000

Data Index: 1128702 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.6299. Min Act: -0.0000

Data Index: 227499 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 2.6661. Min Range: -2.6661

Max Act: 1.9995. Min Act: -0.0000

Data Index: 977239 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.3188. Min Act: -0.0000

Data Index: 570786 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.1772. Min Act: -0.0001

Data Index: 185884 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.1380. Min Act: -0.0000

Data Index: 882766 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.2537. Min Act: -0.0000

Data Index: 574179 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 2.6661. Min Range: -2.6661

Max Act: 1.9914. Min Act: -0.0000

Data Index: 942947 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.1956. Min Act: -0.0000

Data Index: 1199609 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 2.6661. Min Range: -2.6661

Max Act: 2.0884. Min Act: -0.0000

Data Index: 990022 (C4 (Web Text))

Max Activating Token Index: 489