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

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

Neuron 622 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: 1.2805. Min Range: -1.2805

Max Act: 1.2805. Min Act: -0.0001

Data Index: 1327469 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.2390. Min Act: -0.0001

Data Index: 586917 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.2202. Min Act: -0.0001

Data Index: 181738 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0719. Min Act: -0.0001

Data Index: 1345257 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1029. Min Act: -0.0001

Data Index: 286218 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0435. Min Act: -0.0001

Data Index: 595489 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0419. Min Act: -0.0001

Data Index: 309551 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0160. Min Act: -0.0001

Data Index: 257491 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0323. Min Act: -0.0001

Data Index: 163246 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9921. Min Act: -0.0001

Data Index: 64464 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9484. Min Act: -0.0001

Data Index: 1274083 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0263. Min Act: -0.0001

Data Index: 7538 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9231. Min Act: -0.0001

Data Index: 769982 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8983. Min Act: -0.0001

Data Index: 465649 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8671. Min Act: -0.0001

Data Index: 765231 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.7833. Min Act: -0.0001

Data Index: 468137 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8529. Min Act: -0.0001

Data Index: 866882 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9154. Min Act: -0.0001

Data Index: 1337629 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9030. Min Act: -0.0001

Data Index: 1271056 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.7795. Min Act: -0.0001

Data Index: 812684 (C4 (Web Text))

Max Activating Token Index: 617