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

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

Neuron 4020 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: 1.2465. Min Range: -1.2465

Max Act: 1.1879. Min Act: -0.0000

Data Index: 845117 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.2281. Min Act: -0.0000

Data Index: 780956 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.2465. Min Act: -0.0000

Data Index: 938281 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1046243 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.1996. Min Act: -0.0000

Data Index: 1219194 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.2194. Min Act: -0.0001

Data Index: 338722 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0736. Min Act: -0.0000

Data Index: 612845 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0965. Min Act: -0.0001

Data Index: 505255 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0193. Min Act: -0.0000

Data Index: 1214553 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.1146. Min Act: -0.0001

Data Index: 152324 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0741. Min Act: -0.0000

Data Index: 336461 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1300459 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0508. Min Act: -0.0000

Data Index: 292163 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.2465. Min Range: -1.2465

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1049427 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0698. Min Act: -0.0001

Data Index: 549113 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0596. Min Act: -0.0000

Data Index: 161560 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0651. Min Act: -0.0000

Data Index: 323804 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.1101. Min Act: -0.0001

Data Index: 575526 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 1.2465. Min Range: -1.2465

Max Act: 1.0471. Min Act: -0.0000

Data Index: 459647 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.2465. Min Range: -1.2465

Max Act: 0.9797. Min Act: -0.0001

Data Index: 1074628 (C4 (Web Text))

Max Activating Token Index: 304