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

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

Neuron 3727 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.3600. Min Act: -0.0001

Data Index: 587253 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.4778. Min Act: -0.0001

Data Index: 240682 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.1544. Min Act: -0.0001

Data Index: 688055 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.3471. Min Act: -0.0001

Data Index: 546233 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0814. Min Act: -0.0001

Data Index: 316312 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.1899. Min Act: -0.0001

Data Index: 1283396 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.3997. Min Act: -0.0001

Data Index: 686818 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2492. Min Act: -0.0001

Data Index: 669555 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2980. Min Act: -0.0001

Data Index: 1269714 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2716. Min Act: -0.0001

Data Index: 301455 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2121. Min Act: -0.0001

Data Index: 156820 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.5975. Min Act: -0.0001

Data Index: 1270360 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2134. Min Act: -0.0001

Data Index: 1297569 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.3393. Min Act: -0.0001

Data Index: 107520 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.1698. Min Act: -0.0001

Data Index: 1098197 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0843. Min Act: -0.0001

Data Index: 663230 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.0715. Min Act: -0.0001

Data Index: 399029 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2182. Min Act: -0.0001

Data Index: 169127 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2589. Min Act: -0.0001

Data Index: 479283 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 1.5975. Min Range: -1.5975

Max Act: 1.2687. Min Act: -0.0001

Data Index: 947464 (C4 (Web Text))

Max Activating Token Index: 146