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

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

Neuron 1331 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: 4.1294. Min Range: -4.1294

Max Act: 4.1294. Min Act: -0.0001

Data Index: 917312 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 4.1294. Min Range: -4.1294

Max Act: 4.1294. Min Act: -0.0001

Data Index: 220081 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 4.1294. Min Range: -4.1294

Max Act: 4.0097. Min Act: -0.0001

Data Index: 1020596 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.9237. Min Act: -0.0001

Data Index: 1105476 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6406. Min Act: -0.0001

Data Index: 893277 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7726. Min Act: -0.0001

Data Index: 926357 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7577. Min Act: -0.0001

Data Index: 603037 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.5862. Min Act: -0.0001

Data Index: 89644 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.8421. Min Act: -0.0001

Data Index: 613359 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6513. Min Act: -0.0001

Data Index: 801450 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6326. Min Act: -0.0001

Data Index: 1126111 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6295. Min Act: -0.0001

Data Index: 863638 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6070. Min Act: -0.0001

Data Index: 1238042 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.7614. Min Act: -0.0001

Data Index: 722984 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6047. Min Act: -0.0001

Data Index: 367899 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.5107. Min Act: -0.0001

Data Index: 74148 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.4872. Min Act: -0.0001

Data Index: 86455 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6477. Min Act: -0.0001

Data Index: 636480 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6197. Min Act: -0.0001

Data Index: 987291 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 4.1294. Min Range: -4.1294

Max Act: 3.6320. Min Act: -0.0001

Data Index: 188414 (C4 (Web Text))

Max Activating Token Index: 311