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

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

Neuron 1762 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: 3.6063. Min Range: -3.6063

Max Act: 3.2295. Min Act: -0.0001

Data Index: 885390 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.5924. Min Act: -0.0001

Data Index: 1162618 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.5100. Min Act: -0.0001

Data Index: 1593686 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.1858. Min Act: -0.0001

Data Index: 85429 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.3306. Min Act: -0.0001

Data Index: 619791 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.2794. Min Act: -0.0001

Data Index: 596237 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.3609. Min Act: -0.0001

Data Index: 1066725 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.1622. Min Act: -0.0001

Data Index: 1458581 (Python Code)

Max Activating Token Index: 796

Text #8

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.6063. Min Act: -0.0001

Data Index: 434358 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.2214. Min Act: -0.0001

Data Index: 334600 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.2840. Min Act: -0.0001

Data Index: 457995 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 3.6063. Min Range: -3.6063

Max Act: 3.0743. Min Act: -0.0001

Data Index: 1053802 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.9176. Min Act: -0.0001

Data Index: 1185721 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.7824. Min Act: -0.0001

Data Index: 459022 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.8991. Min Act: -0.0001

Data Index: 227847 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.4613. Min Act: -0.0001

Data Index: 579639 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.4509. Min Act: -0.0001

Data Index: 164119 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.6974. Min Act: -0.0001

Data Index: 1607815 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.8326. Min Act: -0.0001

Data Index: 484 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 3.6063. Min Range: -3.6063

Max Act: 2.9160. Min Act: -0.0001

Data Index: 1293837 (C4 (Web Text))

Max Activating Token Index: 186