Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 737 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1866. Min Range: -1.1866

Max Act: 1.1866. Min Act: -0.0001

Data Index: 101454 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.1866. Min Range: -1.1866

Max Act: 1.0720. Min Act: -0.0001

Data Index: 1233487 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.1866. Min Range: -1.1866

Max Act: 1.0129. Min Act: -0.0001

Data Index: 1229639 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9172. Min Act: -0.0001

Data Index: 593394 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9694. Min Act: -0.0001

Data Index: 25441 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 1.1866. Min Range: -1.1866

Max Act: 1.0353. Min Act: -0.0001

Data Index: 549100 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.7671. Min Act: -0.0001

Data Index: 734353 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8297. Min Act: -0.0001

Data Index: 410817 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.7915. Min Act: -0.0001

Data Index: 277565 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8712. Min Act: -0.0001

Data Index: 91035 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8033. Min Act: -0.0001

Data Index: 864188 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9049. Min Act: -0.0001

Data Index: 88165 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8421. Min Act: -0.0001

Data Index: 230750 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.7963. Min Act: -0.0001

Data Index: 1225668 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8677. Min Act: -0.0001

Data Index: 909812 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8058. Min Act: -0.0001

Data Index: 96845 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1198655 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8129. Min Act: -0.0001

Data Index: 404255 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.7710. Min Act: -0.0001

Data Index: 1163600 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.7914. Min Act: -0.0001

Data Index: 438884 (C4 (Web Text))

Max Activating Token Index: 359