Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 514 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.8068. Min Act: -0.0001

Data Index: 1348844 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.5776. Min Act: -0.0001

Data Index: 754155 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.5298. Min Act: -0.0001

Data Index: 762160 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.3779. Min Act: -0.0001

Data Index: 773669 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.3765. Min Act: -0.0001

Data Index: 1120752 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2879. Min Act: -0.0001

Data Index: 1250957 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.4098. Min Act: -0.0001

Data Index: 616191 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.3168. Min Act: -0.0001

Data Index: 119838 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.3147. Min Act: -0.0001

Data Index: 907838 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2710. Min Act: -0.0001

Data Index: 459564 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2629. Min Act: -0.0001

Data Index: 838021 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2879. Min Act: -0.0001

Data Index: 753245 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2728. Min Act: -0.0001

Data Index: 1243426 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2457. Min Act: -0.0001

Data Index: 1079613 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2420. Min Act: -0.0001

Data Index: 911383 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.1999. Min Act: -0.0001

Data Index: 240584 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.1530. Min Act: -0.0001

Data Index: 118629 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.1658. Min Act: -0.0001

Data Index: 223122 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.2509. Min Act: -0.0001

Data Index: 1030768 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.8068. Min Range: -1.8068

Max Act: 1.1723. Min Act: -0.0001

Data Index: 152312 (C4 (Web Text))

Max Activating Token Index: 63