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

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

Neuron 221 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: 1.4803. Min Range: -1.4803

Max Act: 1.4803. Min Act: -0.0000

Data Index: 287286 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1804. Min Act: -0.0001

Data Index: 870129 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.4456. Min Act: -0.0001

Data Index: 1285820 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.2404. Min Act: -0.0001

Data Index: 889700 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1007034 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.2569. Min Act: -0.0000

Data Index: 417947 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.3193. Min Act: -0.0000

Data Index: 922040 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1801. Min Act: -0.0001

Data Index: 305384 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.2179. Min Act: -0.0001

Data Index: 364688 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1933. Min Act: -0.0001

Data Index: 1054244 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1036. Min Act: -0.0001

Data Index: 696458 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1878. Min Act: -0.0001

Data Index: 1231 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1671. Min Act: -0.0001

Data Index: 1107880 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1760. Min Act: -0.0001

Data Index: 1056673 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0944. Min Act: -0.0001

Data Index: 225199 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0777. Min Act: -0.0000

Data Index: 729797 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0541. Min Act: -0.0000

Data Index: 907641 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1860. Min Act: -0.0001

Data Index: 1019170 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0795. Min Act: -0.0001

Data Index: 1034533 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1225149 (C4 (Web Text))

Max Activating Token Index: 681