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

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

Neuron 462 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: 1.5581. Min Range: -1.5581

Max Act: 1.5581. Min Act: -0.0001

Data Index: 869362 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.3636. Min Act: -0.0001

Data Index: 324242 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1305120 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.4106. Min Act: -0.0000

Data Index: 18466 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.0981. Min Act: -0.0001

Data Index: 412880 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2043. Min Act: -0.0001

Data Index: 1060757 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.3059. Min Act: -0.0001

Data Index: 307191 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2540. Min Act: -0.0001

Data Index: 570274 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2589. Min Act: -0.0001

Data Index: 334607 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.3391. Min Act: -0.0000

Data Index: 701240 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.3582. Min Act: -0.0001

Data Index: 498093 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2944. Min Act: -0.0001

Data Index: 821096 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.3274. Min Act: -0.0000

Data Index: 924588 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2744. Min Act: -0.0000

Data Index: 112246 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.3391. Min Act: -0.0001

Data Index: 341205 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1081276 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2137. Min Act: -0.0001

Data Index: 323349 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1099001 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.2155. Min Act: -0.0001

Data Index: 1299251 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 1.5581. Min Range: -1.5581

Max Act: 1.1713. Min Act: -0.0001

Data Index: 1250544 (C4 (Web Text))

Max Activating Token Index: 244