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

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

Neuron 1157 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6751. Min Act: -0.0000

Data Index: 382253 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6575. Min Act: -0.0000

Data Index: 171895 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6317. Min Act: -0.0000

Data Index: 165363 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5739. Min Act: -0.0000

Data Index: 229889 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1302904 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1216941 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1122587 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4949. Min Act: -0.0000

Data Index: 351575 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1299004 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5058. Min Act: -0.0000

Data Index: 276580 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1295023 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5198. Min Act: -0.0000

Data Index: 316957 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4651. Min Act: -0.0000

Data Index: 468489 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1178226 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4935. Min Act: -0.0000

Data Index: 752033 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4530. Min Act: -0.0000

Data Index: 128200 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1070169 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1033921 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1177320 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4551. Min Act: -0.0000

Data Index: 759821 (C4 (Web Text))

Max Activating Token Index: 95