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

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

Neuron 4693 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.7112. Min Act: -0.0000

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.5782. Min Act: -0.0000

Data Index: 163890 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.5413. Min Act: -0.0000

Data Index: 557625 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.2517. Min Act: -0.0000

Data Index: 1090141 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.4103. Min Act: -0.0000

Data Index: 838837 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.5697. Min Act: -0.0000

Data Index: 199710 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.5290. Min Act: -0.0000

Data Index: 982073 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.3418. Min Act: -0.0000

Data Index: 1295315 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.1705. Min Act: -0.0000

Data Index: 698571 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.3242. Min Act: -0.0000

Data Index: 738107 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.3418. Min Act: -0.0000

Data Index: 294856 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.1235. Min Act: -0.0000

Data Index: 643489 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.2741. Min Act: -0.0000

Data Index: 1104146 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.2661. Min Act: -0.0000

Data Index: 879219 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.2603. Min Act: -0.0000

Data Index: 325105 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.0797. Min Act: -0.0000

Data Index: 1198170 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.0444. Min Act: -0.0000

Data Index: 605993 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.2399. Min Act: -0.0000

Data Index: 205611 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.2186. Min Act: -0.0000

Data Index: 1219913 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 4.7112. Min Range: -4.7112

Max Act: 4.0000. Min Act: -0.0000

Data Index: 957386 (C4 (Web Text))

Max Activating Token Index: 176